The DOI matches its Crossref record; 69 of the 78 references it cites were found in a registry or an index; 13 of the 34 sources its claims cite were checked for support.
WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving
Open accessAbstract
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications. In spite of their prevalence, there are few public datasets for detailed evaluation of computer vision algorithms on fisheye images. We release the first extensive fisheye automotive dataset, WoodScape, named after Robert Wood who invented the fisheye camera in 1906. WoodScape comprises of four surround view cameras and nine tasks including segmentation, depth estimation, 3D bounding box detection and soiling detection. Semantic annotation of 40 classes at the instance level is provided for over 10,000 images and annotation for other tasks are provided for over 100,000 images. With WoodScape, we would like to encourage the community to adapt computer vision models for fisheye camera instead of using naive rectification.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
WoodScape is introduced as a multi-task, multi-camera fisheye dataset for autonomous driving, with four 190° horizontal-FOV cameras, LiDAR, GNSS/IMU, and annotations for nine tasks. It provides baseline results across segmentation, detection, depth, motion, soiling, odometry/SLAM, and 3D boxes, while arguing for native fisheye models rather than undistortion.
Key findings
- The dataset contains over 10,000 images with instance-level semantic annotation, four 1MPx RGB fisheye cameras covering 360°, one Velodyne HDL-64E LiDAR at 20 Hz, GNSS/IMU, and labels for nine tasks including semantic segmentation, 2D/3D detection, depth, motion segmentation, soiling detection, visual odometry/SLAM, and end-to-end driving.
- Baseline results include ENet segmentation IoU 51.4, Faster R-CNN 2D detection mAP 31 at IoU ≥ 0.5, ResNet10 soiling category precision 84.5%, Eigen depth RMSE 7.7, MODNet motion segmentation IoU 45, visual odometry translation <5 mm 51% and rotation <0.1° 71%, and LSD-SLAM relocalization 61%.
- For 3D bounding box detection, Complex-YOLO trained with the proposed S_srt metric achieved AP 62.46%, AOS 88.43%, and runtime 1 ms, versus 3D-IoU training with AP 64.38%, AOS 85.60%, and runtime 95 ms, improving training time by 95×.
- A pre-trained person detector achieved mAP 12 on fisheye images versus 45 for a model trained on WoodScape, which the authors use to argue that fisheye geometry must be handled explicitly.
Methods
- The dataset was captured from three geographical locations (USA, Europe, China), with highway, urban, and parking scenarios, saloon and sports utility vehicles, and intrinsic/extrinsic calibration plus timestamp synchronization.
- Annotation covers 40 semantic classes, 5k soiling images, 10k 3D box frames, 400k depth frames, 10k motion segmentation frames, 50 video sequences with over 100k frames for VO/SLAM, 500 end-to-end driving videos, and 10k synthetic frames.
- Data splitting is 6:1:3 training/validation/testing, with five splits and task-specific stratified splits; sampling uses a wrapper method based on classifier accuracy plus a filter based on image similarity. Baselines use ENet, Faster R-CNN with ResNet101, ResNet10, Eigen, MODNet, LSD-SLAM, and Complex-YOLO.
Limitations
- The paper states that 2D bounding box detection mAP of 31 is significantly lower than on other datasets and that incorporating fisheye geometry explicitly remains an open research problem.
- The paper states that spherical models do not accurately fit fisheye lenses and that adapting CNNs to fisheye distortion is an open problem; it also notes that simultaneous annotation is provided for various tasks but with exceptions due to practical limitations of optimal dataset design.
- The paper states that more than one third of the dataset is recorded in Europe and is GDPR-sensitive due to visible faces and license plates, so it follows a license-agreement approach rather than blurring or GAN retargeting; it also states that end-to-end steering/braking is not currently mature for deployment.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
13 of 34 cited sources checked · 0 supported · 1 flagged · accuracy not yet measured
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“We run the semi-supervised approach from [33] using the model proposed by Eigen [14] as baseline on our much larger dataset and obtained an RMSE (Root Mean Square Error) value of 7.7.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.5. Monocular Depth Estimation
What the sources say
- Not checked — no full text of the sourcecites [33] source
- Disputedcites [14] sourceExperimental — accuracy not yet measured
The citation in the sentence attributes the semi-supervised approach to this source; the RMSE is presented as the citing authors’ own result. Section 2 (pp. 2–3) instead describes training a network on images paired with human steering commands to predict steering, not a semi-supervised approach to monocular depth estimation. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“| Soiling Detection | ResNet10 [20] | Category (%) | 84.5 |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
What the sources say
- Could not verifycites [20] sourceExperimental — accuracy not yet measured
The paper’s discussion of classification methods (III. Vision Algorithm Building Blocks, p. 4) and its table of established applications (p. 5) do not report a soiling-detection result. Searches for WoodScape, ResNet10, and 84.5 found no passage supporting the attributed dataset, model, or score. (LLM, conf=0.76)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Depending on the particular task (see Section 4, for the full list), the class imbalance may be an issue [19], therefore, task-specific splits are also provided.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Data splitting and class balancing:
What the sources say
- Partly supportedcites [19] sourceExperimental — accuracy not yet measured
Section 5.1 (p. 12) identifies a class-imbalance problem: traffic lights occur less often than light poles, and the authors suggest better class-balancing strategies. Section 5.2 (p. 12) describes separate task benchmarks and dataset splits, but does not say those splits were provided because of class imbalance. (LLM, conf=0.84)
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“| Visual Odometry | ResNet50 [20] | Translation (<5mm) Rotation (<0.1°) | 51 71 |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
What the sources say
- Could not verifycites [20] sourceExperimental — accuracy not yet measured
The discussion of odometry in 'Towards a generic scalable algorithm framework' (p. 6) concerns its use in segmenting moving objects, not a performance evaluation. Searches for WoodScape, ResNet50, and the claimed translation threshold and score found no passage in our copy reporting that result. (LLM, conf=0.77)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“| Visual Odometry | ResNet50 [20] | Translation (<5mm) Rotation (<0.1°) | 51 71 |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
What the sources say
- Could not verifycites [20] sourceExperimental — accuracy not yet measured
The Motion Estimation section (p. 3) describes tracking and matching image pixels, but reports no visual-odometry benchmark score. Searches for WoodScape, ResNet50, and the stated rotation and translation thresholds found no passage supporting the score of 71. (LLM, conf=0.76)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“First fisheye dataset comprising of over 10,000 images containing instance level semantic annotation.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Proposal of an efficient metric for the 3D box detection task which improves training time by 95x.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Annotations are made available for nine tasks, notably 3D object detection, depth estimation (overlaid on front camera) and semantic segmentation as illustrated here.”
- Also stated in: § 3.2. Dataset Acquisition · plain
“Our WoodScape dataset provides labels for several autonomous driving tasks including semantic segmentation, monocular depth estimation, object detection (2D & 3D bounding boxes), visual odometry, visual SLAM, motion segmentation, soiling detection and end-to-end driving (driving controls).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 3.2. Dataset Acquisition · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our model is based on a fourth order polynomial mapping incident angle to image radius in pixels (r(θ) = a 1 θ + a 2 θ 2 + a 3 θ 3 + a 4 θ 4 ).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We have designed our dataset so that simultaneous annotation is provided for various tasks with some exceptions due to practical limitations of optimal dataset design for each task.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- It may state two separate claims as one. 36
- Probably not a substantial claim. 19
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“There are very few public fisheye datasets and none of them provide semantic segmentation annotation.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
What the sources say
- Could not verifycites [7] sourceExperimental — accuracy not yet measured
The RobotCar Platform (p. 1) describes fisheye cameras, and the paper says the dataset is available for download. But the Introduction (p. 1) does not assess how many public fisheye datasets exist, and searches for semantic-segmentation annotations found no passage saying that none provide them. (LLM, conf=0.72)
- Not checked — no full text of the sourcecites [9] source
- Not matchedcites [37]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In the recent EuroCity persons dataset [5], the authors argued that any anonymization measure will introduce a bias.Thus they released their dataset with original data and a license agreement which enforces the user to strictly adhere to GDPR.We will follow a similar approach.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > GDPR challenges:
What the sources say
- Could not verifycites [5] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Bojarski et al. demonstrated end-to-end learning [2] for steering and recently it was applied to fisheye cameras [54].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.9. End-to-End Steering/Braking
What the sources say
- Not checked — no full text of the sourcecites [2] source
- Could not verifycites [54] sourceExperimental — accuracy not yet measured
The Abstract and Introduction discuss semantic segmentation, but neither addresses end-to-end steering with fisheye cameras. Searches for fisheye steering and Bojarski found no relevant passage in our copy. (LLM, conf=0.76)
Strength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“There are several popular synthetic datasets like SYNTHIA [44] and CARLA [13].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.8. Synthetic Data Domain Transfer
What the sources say
- Could not verifycites [44] sourceExperimental — accuracy not yet measured
The citation is attached to SYNTHIA, but the passages from “Selecting Representative Data Sets” (page unavailable) discuss representative-set selection and SMOTE synthetic instances, not SYNTHIA. Searches for SYNTHIA and CARLA found no passage identifying either dataset or addressing its popularity. (LLM, conf=0.76)
- Not matchedcites [13]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Semantic segmentation networks for autonomous driving [47] have been successfully trained directly on fisheye images in [12,45].Due to absence of fisheye datasets, they make use of artificially warped images of Cityscapes for training and testing was performed on fisheye images.However, the artificial images cannot increase the originally captured FOV.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.1. Semantic Segmentation
What the sources say
- Could not verifycites [47] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked — no full text of the sourcecites [12] source
- Not checked — no full text of the sourcecites [45] source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: Artificially warped images cannot increase the originally captured field of view.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“This has been explored in [49,57,48] for narrow angle cameras.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.6. Motion Segmentation
What the sources say
- Not matchedcites [49]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [57]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Could not verifycites [48] sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes semantic segmentation for automated driving, and the Auxiliary Task Learning section (p. 3) illustrates optical flow as a possible task. Searches for motion segmentation and narrow-angle cameras found no passage saying this paper explored motion segmentation with such cameras. (LLM, conf=0.73)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The dataset supports correct hypothesis evaluation [55], therefore multiple splits are provided (5 in total).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Data splitting and class balancing:
What the sources say
- Could not verifycites [55] sourceExperimental — accuracy not yet measured
The section on large annotated datasets discusses CamVid, Cityscapes and other datasets, but not WoodScape. The benchmarking section describes an evaluation on CamVid; neither it nor the other passages found addresses WoodScape’s support for hypothesis evaluation or its five splits (searched: WoodScape, hypothesis evaluation, dataset splits). (LLM, conf=0.76)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In general, 3D IoU [18] is used to evaluate 3D bounding box predictions”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.4. 3D Bounding Box Detection
What the sources say
- Could not verifycites [18] sourceExperimental — accuracy not yet measured
Section 4.6, “A note on accuracy” (p. 11), discusses detection and localisation accuracy for automated parking, but does not identify 3D IoU as an evaluation metric. Searches for 3D IoU, intersection over union, and bounding-box evaluation found no passage addressing the claim. (LLM, conf=0.78)
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
- Could not verify
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In our experience, higher orders provide no additional accuracy.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In WoodScape, we provide model parameters for a more generic fisheye intrinsic calibration that is independent of any specific projection model, and does not require the added step of distortion correction.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Introduction of a novel soiling detection task and release of first dataset of its kind.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It contains four cameras covering 360 ° accompanied by a HD laser scanner, IMU and GNSS.”
- Also stated in: § 1. Introduction · plain
“WoodScape is a comprehensive dataset for 360 ° sensing around a vehicle using the four fisheye cameras shown in Figure 2.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Also stated in: § 1. Introduction · plain
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Four-camera nine-task dataset designed to encourage unified multi-task and multi-camera models.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The plot indicates that the difference to the original fourth order polynomial is about four pixels for UCM and one pixel for eUCM for low incident angles.For larger incident angles, these models are less precise.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Strength:hedged· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We introduce WoodScape, the first fisheye image dataset dedicated to autonomous driving.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While the majority of data was obtained from saloon vehicles there is a significant subset from a sports utility vehicle ensuring a strong mix in sensor mechanical configurations.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“More than one third of our dataset is recorded in Europe and is therefore GDPR sensitive due to visible faces of pedestrians and license plates.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > GDPR challenges:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Driving scenarios are divided across the highway, urban driving and parking use cases.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The video sequences can also be used for Visual SLAM where we focus on relocalization of a mapped trajectory and the metric is same as VO.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.7. Visual Odometry/SLAM
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Even though this comparison uses 3D-IoU, we achieve similar performance for average precision (3D-IoU), with better angle orientation similarity (AOS) and much faster computation time.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.4. 3D Bounding Box Detection
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The dataset also provides a set of synthetic data using accurate models of the real cameras, enabling investigations of additional tasks.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Thus we have added end-to-end steering and braking tasks to encourage modular end-to-end architectures and to explore optimized perception for the control task.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.9. End-to-End Steering/Braking
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We provide 50 video sequences comprising of over 100k frames with ground truth.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.7. Visual Odometry/SLAM
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Images are provided at 1MPx 24-bit resolution and videos are uncompressed at 30fps ranging in duration from 30s to 120s.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“• 4x 1MPx RGB fisheye cameras (190 • horizontal FOV) • 1x LiDAR rotating at 20Hz (Velodyne HDL-64E) • 1x GNSS/IMU (NovAtel Propak6 & SPAN-IGM-A1) • 1x GNSS Positioning with SPS (Garmin 18x) • Odometry signals from the vehicle bus.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Intrinsic and extrinsic calibrations are provided for all sensors as well as timestamp files to allow synchronization of the data.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“| Segmentation | Classes Frames | 8 400 | 30 5k | 66 25k | -- | 25 140k | 40 5.7k | 40 10k |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We achieve a mAP score of 31 which is significantly less than the accuracy achieved in other datasets.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.2. 2D Bounding Box Detection
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“We also provide previous and next images for exploring multi-stream models like MOD-Net [49].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.6. Motion Segmentation
What the sources say
- Not checked — no full text of the sourcecites [49] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition to providing fisheye data, we provide data for many more tasks than is typical (nine in total), providing completely novel tasks such as soiled lens detection.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“3D box annotation is provided for 10k frames with 3 classes namely 'pedestrian', 'vehicle' and 'cyclist'.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.4. 3D Bounding Box Detection
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We provide more than 100k images of all four cameras (totaling 400k) using ground truth provided by LiDAR.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.5. Monocular Depth Estimation
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“| 2D Bounding Box 1 | Classes Frames | 3 15k | -- | -- | -- | -- | 10 5.7k | 7 10k |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“Fisheye is particularly beneficial to automotive low speed manoeuvring scenarios such as parking [21] where accurate full coverage near field sensing can be achieved with just four cameras.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
What the sources say
- Not matchedcites [21]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Not matched
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“However, spherical models do not provide an accurate fit for fisheye lenses and it is an open problem.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
What the sources say
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Because of fundamental limitations of undistortion, an alternate approach of adapting the algorithm incorporating fisheye model discussed in previous section could be an optimal solution.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This advantage comes with some drawbacks in the significantly more complex projection geometry that fisheye cameras exhibit.That is, images from fisheye cameras display severe distortion.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2. Overview of Fisheye Camera Projections
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Firstly, the FOV is greater than 180 • , hence there are rays incident from behind the camera and it is not possible to establish a complete mapping to a rectilinear viewport.This leads to a loss of FOV, this is seen via the missing yellow pillars in the corrected image.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Given their extremely wide field of view, they can observe the full surrounding of a vehicle with a minimal number of sensors, with just four cameras typi- cally being required for full 360 • coverage (Figure 2).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2. Overview of Fisheye Camera Projections
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Standard computer vision models do not generalize easily to fisheye cameras because of large non-linear distortion.For example, translation invariance is lost for a standard convolutional neural net (CNN).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Existing datasets are primarily designed to facilitate task-specific learning and they don't provide simultaneous annotation for all the tasks.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Full control of the splitting mechanism is provided allowing for each class to be represented equally within each split (i.e.stratified sampling).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Data splitting and class balancing:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Unlike the front camera which is behind the windshield, the surround view cameras are usually directly exposed to the adverse environmental conditions, and thus prone to becoming soiled or water drops forming on the lens.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.3. Camera Soiling Detection
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The classes to detect are {opaque, transparent}.Typically, opaque soiling arises from mud and dust (Figure 8 right image), and transparent soiling arises from water and ice (Figure 8 left image).However, in practice it is common to see water producing”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.3. Camera Soiling Detection
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Rests on an assumption: Opaque soiling typically arises from mud and dust, and transparent soiling from water and ice.
- Rests on an assumption: Water can produce 'opaque' regions in the camera image.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“High-quality data is ensured via quality checks at all stages of the data collection process.Annotation data undergoes a rigorous quality assurance by highly skilled reviewers.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We observe that it is necessary to incorporate the fisheye geometry explicitly, which is an open research problem.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.2. 2D Bounding Box Detection
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Collecting frames at a frame rate of 30fps, particularly at low speeds, ultimately leads to significant image overlap, therefore, having an effective sampling strategy to distill the dataset is critical.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Sampling strategy:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“The task of soiling detection was to our best knowledge first defined in [56].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.3. Camera Soiling Detection
What the sources say
- Not checked — no full text of the sourcecites [56] source
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, at the same time, it was shown that careful inspection of the training sets for outliers improves the robustness of deep neural networks [36], especially with regards to the adversarial examples.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.3. Dataset Design
What the sources say
- Not checked — no full text of the sourcecites [36] source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
In the paper
“Visual Odometry (VO) is necessary for creating a map from the objects detected [38].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.7. Visual Odometry/SLAM
What the sources say
- Not checked — no full text of the sourcecites [38] source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
Surround view systems have at least four cameras rigidly connected to the body of the car.
“Surround view systems have at least four cameras rigidly connected to the body of the car.”
The paper relies on this without support.
Artificially warped images cannot increase the originally captured field of view.
“However, the artificial images cannot increase the originally captured FOV.”
The paper relies on this without support.
Opaque soiling typically arises from mud and dust, and transparent soiling from water and ice.
“Typically, opaque soiling arises from mud and dust (Figure 8 right image), and transparent soiling arises from water and ice (Figure 8 left image).”
The paper relies on this without support.
Water can produce 'opaque' regions in the camera image.
“However, in practice it is common to see water producing”
The paper relies on this without support.
3D IoU has drawbacks, especially for rotated objects.
“In general, 3D IoU [18] is used to evaluate 3D bounding box predictions, but there are drawbacks, especially for rotated objects.”
The paper relies on this without support.
Two boxes can reach a good 3D IoU score while overlapping in total with an opposite heading.
“Two boxes can reach a good 3D IoU score, while overlapping in total with an opposite heading.”
The paper relies on this without support.
Exact calculation in 3D space is time-consuming.
“Additionally, an exact calculation in 3D space is a time consuming task.”
The paper relies on this without support.
Motion is a strong cue in automotive due to ego-motion of cameras and dynamic objects are critical interacting agents.
“In automotive, motion is a strong cue due to ego-motion of the cameras on the moving vehicle and dynamic objects around the vehicle are the critical interacting agents.”
The paper relies on this without support.
Synthetic data is crucial for autonomous driving.
“Synthetic data is crucial for autonomous driving for many reasons.”
The paper relies on this without support.
There are legal restrictions like recording videos of a child.
“Secondly, there are legal restrictions like recording videos of a child.”
The paper relies on this without support.
Synthetic data is the only way to obtain dense depth and optical flow annotation.
“Finally, synthetic data is the only way to obtain dense depth and optical flow annotation.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Other works explored image restoration using inpainting or generative methods [3,4], though such approaches carry risks of hallucinated visual cues that may mislead the perception system.”
From AI-Based Image Quality and Lens Defect Analysis in Autonomous Driving: A Framework with U-Net-Based Soiling Detection (2025) · cites this paper as [4]
Experimental — accuracy not yet measured
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 3×
“7 Motion Segmentation MODNet [49] IoU 45 Visual Odometry ResNet50 [20] Translation (<5mm) 51 Rotation (<0.”
BackgroundMethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We fine-tune their model for our dataset by training with categorical cross entropy loss and Adam [29] optimizer.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 3×
“4 2D Bounding Box Faster R-CNN [43] mAP (IoU>0.”
BackgroundMethodImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“We initialize the network with ImageNet [11] pre-trained weights.”
MethodThe pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 12×
“Performance of 2D object detection is reported in terms of mean average precision (mAP) when IoU≥ 0.5 between predicted and ground truth bounding boxes.”
BackgroundMethodInfluentialThe Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 4×
“Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
BackgroundMethodInfluentialA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1×
“the desired precision. Another, more appropriate, approach is to exchange these regions by some automatically generated proposals. For example, exchanging all faces for automatically generated ones2 [25]. Such anonymized data will not violate GDPR rules as the original person is no longer identifiable. We aim to ensure…”
BackgroundVision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 3×
“Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
Background
Flagged first, then by citations
9 of the 78 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- kumar, 2018, Near-field depth estimation using monocular fisheye camera: A semi-supervised learning approach using sparse LiDAR data, CVPR Workshop
- caruso, 2015, Largescale direct SLAM for omnidirectional cameras, Proceedinsg of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 141
Cited by
Sorted by citations
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00371 · Cited by 11,953
“-20 0 +20 +40 IoU delta at 1 center point GTEA [34, 63] TrashCan [52] DRAM [24] PIDRay [104] Cityscapes [25] WoodScape [112] IBD [17] EgoHOS [113] Plittersdorf [46] VISOR [28, 27] NDISPark [22, 23] Hypersim [86] OVIS [81] ADE20K [117] iShape [111] ZeroWaste-f [6] STREETS [91] LVIS [44] NDD20 [100] TimberSeg [38] DOORS…”
BackgroundMethodInfluentialnuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152
“Similar to [84], nuScenes is a holistic scene understanding benchmark for AVs.”
BackgroundDeep reinforcement learning for autonomous driving: A survey
Kiran, B. R., Sobh, I., Talpaert, V., Mannion, P., Sallab, A. A. A., Yogamani, S., & Perez, P. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3054625 · Cited by 2,342
“into a multi-task model [8], [9].”
Self-citationSensor and Sensor Fusion Technology in Autonomous Vehicles: A Review
Yeong, D. J., Velasco-Hernandez, G., Barry, J., & Walsh, J. L. (2021) · Sensors · doi:10.3390/s21062140 · Cited by 1,187
“Other commonly employed cameras in AVs for perception of the surroundings include fisheye cameras [46-48].”
BackgroundKITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
Liao, Y., Xie, J., & Geiger, A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3179507 · Cited by 770
3D Object Detection for Autonomous Driving: A Comprehensive Survey
Mao, J., Shi, S., Wang, X., & Li, H. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01790-1 · Cited by 529
Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100
Damen, D., Doughty, H., Farinella, G. M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01531-2 · Cited by 400
V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving
Li, Y., Ma, D., An, Z., Wang, Z., Zhong, Y., Chen, S., & Feng, C. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3192802 · Cited by 381
Holistic LSTM for Pedestrian Trajectory Prediction
Quan, R., Zhu, L., Wu, Y., & Yang, Y. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3058599 · Cited by 181
“[47] proposes a fish-eye automotive dataset,”
Active Learning for Domain Adaptation: An Energy-Based Approach
Xie, B., Yuan, L., Li, S., Liu, C. H., Cheng, X., & Wang, G. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20850 · Cited by 153
“This limits their usage in many practical applications, such as autonomous driving with massive unlabeled data (Yogamani et al. 2019) and medical diagnosis with high labeling cost (Ronneberger, Fischer, and Brox 2015).”
BackgroundFord Multi-AV Seasonal Dataset
Agarwal, S., Vora, A., Pandey, G., Williams, W., Kourous, H., & McBride, J. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920961451 · Cited by 146
“Many research groups have relied on camera-based solutions (Davison et al., 2007; Nguyen et al., 2011; Redmon et al., 2016; Schafer et al., 2018; Yogamani et al., 2019) on account of their high resolution and inexpensive nature.”
BackgroundOmniDet: Surround View Cameras Based Multi-Task Visual Perception Network for Autonomous Driving
Ravi Kumar, V., Yogamani, S., Rashed, H., Sitsu, G., Witt, C., Leang, I., Milz, S., & Mader, P. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062324 · Cited by 121
“In the Woodscape fisheye dataset [29], there are 12 different cameras with slight intrinsic variations to evaluate this effect.”
BackgroundMethodSelf-citationReview on Panoramic Imaging and Its Applications in Scene Understanding
Gao, S., Yang, K., Shi, H., Wang, K., & Bai, J. Y. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3216675 · Cited by 121
“other fisheye [324], [325], [326], [327], panoramic [328], [329], [330], and omnidirectional [331], [332], [333], [334]”
PASS: Panoramic Annular Semantic Segmentation
Yang, K., Hu, X., Bergasa, L. M., Romera, E., & Wang, K. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2938965 · Cited by 109
“WoodScape [55] comprises of four fish-eye cameras to observe the full surrounding of an automobile with semantically annotated images originating from distinct geographical locations.”
BackgroundRashed, H., Ramzy, M., Vaquero, V., Sallab, A. E., Sistu, G., & Yogamani, S. K. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00293 · Cited by 116
Self-citationA Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services
Katare, D., Perino, D., Nurmi, J., Warnier, M., Janssen, M., & Ding, A. Y. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3302474 · Cited by 135
Surround-View Fisheye Camera Perception for Automated Driving: Overview, Survey & Challenges
Kumar, V. R., Eising, C., Witt, C., & Yogamani, S. K. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3235057 · Cited by 132
“Wood initially coined the term fisheye in 1908 and constructed a simple fisheye camera [1], a fact that is acknowledged in the naming of the recently released WoodScape dataset of automotive fisheye video [2].”
BackgroundMethodSelf-citationBending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
Zhang, J., Yang, K., Ma, C., Reiß, S., Peng, K., & Stiefelhagen, R. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01641 · Cited by 104
“Outdoor panorama segmentation works rely on fisheye cameras [14, 54, 77, 79] or panoramic images [27, 47, 70, 74] for seamless 360◦ parsing.”
BackgroundEPIC-KITCHENS-100Preprint
Damen, D., Doughty, H., Farinella, G. M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.13256 · Cited by 153
“This has been recently achieved for autonomous driving [17,18,19,20,21,22,23,24] and scene understanding [25,26].”
BackgroundRashed, H., Mohamed, E., Sistu, G., Kumar, V. R., Eising, C., El-Sallab, A., & Yogamani, S. K. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00232 · Cited by 104
“More details are discussed in our WoodScape Dataset paper [32].”
InfluentialSelf-citationHilti-Oxford Dataset: A Millimeter-Accurate Benchmark for Simultaneous Localization and Mapping
Zhang, L., Helmberger, M., Fu, L. F. T., Wisth, D., Camurri, M., Scaramuzza, D., & Fallon, M. F. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3226077 · Cited by 92
“[7] S. Yogamani et al., “WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving,” in Proc.”
InfluentialKumar, V. R., Klingner, M., Yogamani, S. K., Milz, S., Fingscheidt, T., & Maeder, P. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00011 · Cited by 88
Self-citationCapturing Omni-Range Context for Omnidirectional Segmentation
Yang, K., Zhang, J., Reiß, S., Hu, X., & Stiefelhagen, R. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00143 · Cited by 79
“The labeling process is extremely time- and labor-intensive, thus, only few surroundview datasets [52, 63, 76] are publicly accessible and none capture as diverse scenes as contemporary pinhole datasets [38, 58] do.”
BackgroundZhu, S., & Meng, Q. (2022) · Accident Analysis & Prevention · doi:10.1016/j.aap.2022.106769 · Cited by 85
Pano-AVQA: Grounded Audio-Visual Question Answering on 360° Videos
Yun, H., Yu, Y., Yang, W., Lee, K., & Kim, G. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00204 · Cited by 87
“…surge from video-sharing platforms ( e.g ., YouTube) and their applications of omnidirectional perception quickly spread from autonomous vehicles [1, 2], robotics [3, 4] to virtual & augmented reality [5, 6], visual understanding in 360 ◦ videos has warranted serious attentions in computer…”
Kumar, V. R., Hiremath, S. A., Bach, M., Milz, S., Witt, C., Pinard, C., Yogamani, S. K., & Mäder, P. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197319 · Cited by 74
“TABLE I Quantitative results of leaderboard algorithms on KITTI dataset [23] and FisheyeDistanceNet on Fisheye dataset part of WoodScape [1].”
MethodInfluentialSelf-citationLet’s Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving
Uricar, M., Sistu, G., Rashed, H., Vobecky, A., Kumar, V. R., Krizek, P., Burger, F., & Yogamani, S. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00081 · Cited by 66
“• Public release of an artificial soiling dataset as a companion to the recently published WoodScape Dataset [33], coined Dirty WoodScape Dataset , to encourage further research in this area.”
MethodInfluentialSelf-citationOmnisupervised Omnidirectional Semantic Segmentation
Yang, K., Hu, X., Fang, Y., Wang, K., & Stiefelhagen, R. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3023331 · Cited by 60
“datasets [17][18][19], but their scene diversity and annotation density are far lower than popular pinhole databases [10][11].”
BackgroundSynWoodScape: Synthetic Surround-View Fisheye Camera Dataset for Autonomous Driving
Sekkat, A. R., Dupuis, Y., Kumar, V. R., Rashed, H., Yogamani, S. K., Vasseur, P., & Honeiné, P. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3188106 · Cited by 64
“To generate the fisheye images, we used a framework based on the cubemap representation of a 360° image and the calibration model proposed in the WoodScape dataset [26].”
MethodInfluentialSelf-citationExternal multi-modal imaging sensor calibration for sensor fusion: A review
Qiu, Z., Martínez-Sánchez, J., Arias, P., & Rashdi, R. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101806 · Cited by 69
Waymo Open Dataset: Panoramic Video Panoptic Segmentation
Mei, J., Zhu, A. Z., Yan, X., Yan, H. R., Qiao, S., Chen, L.-C., & Kretzschmar, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19818-2_4 · Cited by 74
FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection
Gochoo, M., Otgonbold, M.-E., Ganbold, E., Hsieh, J.-W., Chang, M., Chen, P.-Y., Dorj, B., Jassmi, H. A., Batnasan, G., Alnajjar, F., et al. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00559 · Cited by 68
“2K 13297 D,Seg + + Surveillance RGB&Thermal MIO-TCD CCTV 2018 [13] 113K 200K D + + 5 Surveillance 2D BDD100k Adas 2018 [25] 100K 250K D,Seg + + 10 Car 2D Woodscape 2018/2019 [24] 10K - D,3D,T + + 7 Car Fish-Eye CityFlow2D 2021 [15] - 313.”
MethodInfluentialIs Context-Aware CNN Ready for the Surroundings? Panoramic Semantic Segmentation in the Wild
Yang, K., Hu, X., & Stiefelhagen, R. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3048682 · Cited by 57
“While there are a few wide-angle databases such as TorontoCity [51] and WoodScape [52], their scene variety and annotation density are far lower than pinhole benchmark datasets like Cityscapes [5], Mapillary Vistas [6], IDD [53] and BDD [54], which suppose”
BackgroundRizzoli, G., Barbato, F., & Zanuttigh, P. (2022) · Technologies · doi:10.3390/technologies10040090 · Cited by 58
A Survey on Datasets for the Decision Making of Autonomous Vehicles
Wang, Y., Han, Z., Xing, Y., Xu, S., & Wang, J. (2024) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2023.3341952 · Cited by 67
“The standards for judging whether interaction exists are also different, e.g., route conflictions [9], [60], specific sets of actions [39], the possibility of hazard [17], or just the presence of surrounding agents [14].”
BackgroundSoilingNet: Soiling Detection on Automotive Surround-View Cameras
Uricar, M., Krizek, P., Sistu, G., & Yogamani, S. (2019) · 2019 IEEE Intelligent Transportation Systems Conference (ITSC) · doi:10.1109/itsc.2019.8917178 · Cited by 55
“duced in our WoodScape dataset paper [15].”
BackgroundSelf-citationUniversal Semantic Segmentation for Fisheye Urban Driving Images
Ye, Y., Yang, K., Xiang, K., Wang, J., & Wang, K. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283099 · Cited by 56
“WoodScape [16], a multi-task, multi-camera fisheye dataset for autonomous driving, and OmniScape [17], a synthetic dataset, could meet our requirement, but they have not been released yet.”
Unifying Panoptic Segmentation for Autonomous Driving
Zendel, O., Schörghuber, M., Rainer, B., Murschitz, M., & Beleznai, C. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.02066 · Cited by 56
“The Raincouver Scene Parsing benchmark [34], Dark Zurich dataset [31], ADUULM dataset [26], the BDD100K dataset [38], the synthetic FoggyCityscapes [30], and the Woodscape dataset [37] present driving scenes each adding some adverse condition (fog, rain, daytime, dusk, night).”
MethodNear-Field Perception for Low-Speed Vehicle Automation Using Surround-View Fisheye Cameras
Eising, C., Horgan, J., & Yogamani, S. K. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3127646 · Cited by 58
“Mostly, though not ubiquitously, we will use the WoodScape Dataset [20].”
BackgroundMethodInfluentialSelf-citationKumar, V. R., Yogamani, S. K., Bach, M., Witt, C., Milz, S., & Mäder, P. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340732 · Cited by 50
“The WoodScape [35] dataset distribution can be found in our FisheyeDistanceNet paper [1].”
MethodSelf-citationA Review of the Impact of Rain on Camera-Based Perception in Automated Driving Systems
Brophy, T., Mullins, D., Parsi, A., Horgan, J., Ward, E., Denny, P., Eising, C., Deegan, B. M., Glavin, M., & Jones, E. (2023) · IEEE Access · doi:10.1109/access.2023.3290143 · Cited by 52
Self-citationLopes, A., de Souza, R. M., & Pedrini, H. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103489 · Cited by 52
“Woodscape Yogamani et al. (2019) 2019 Driving SOR and SOE LiDAR Velodyne HDL-64E Color, IMU, GPS, Depth Instance”
Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems
Leang, I., Sistu, G., Bürger, F., Bursuc, A., & Yogamani, S. K. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294676 · Cited by 43
“on the wide range of tasks from the WoodScape dataset [57].”
BackgroundMethodSelf-citationSVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras
Kumar, V. R., Klingner, M., Yogamani, S. K., Bach, M., Milz, S., Fingscheidt, T., & Mäder, P. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3088950 · Cited by 47
“TABLE III: Ablation study on multiple cameras concerning the usage of Camera Geometry Tensor using WoodScape [3].”
InfluentialSelf-citationSELMA: SEmantic Large-Scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints
Testolina, P., Barbato, F., Michieli, U., Giordani, M., Zanuttigh, P., & Zorzi, M. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3257086 · Cited by 41
“Namely, WoodScape [48] is among the first and most complete datasets providing both LiDAR and fisheye captures, where the omnidirectional view of the surroundings is obtained combining the 4 fisheye cameras.”
BackgroundAloraini, F., Javed, A., & RANA, O. F. (2024) · Sensors · doi:10.3390/s24123848 · Cited by 50
A Literature Review of Performance Metrics of Automated Driving Systems for On-Road Vehicles
Sharath, M. N., & Mehran, B. (2021) · Frontiers in Future Transportation · doi:10.3389/ffutr.2021.759125 · Cited by 41
“Visual cues such as lane markings and traf fi c signs can be perceived using cameras (Pollard et al., 2011; Yogamani et al., 2019).”
BackgroundFisheyeDet: A Self-Study and Contour-Based Object Detector in Fisheye Images
Li, T., Tong, G., Tang, H., Li, B., & Chen, B. (2020) · IEEE Access · doi:10.1109/access.2020.2987868 · Cited by 36
“These works have obtained satisfactory results, especially in pedestrians and vehicles [17]–[20].”
Seeing through obstructions with diffractive cloaking
Shi, Z., Bahat, Y., Baek, S., et al. (2022) · ACM Transactions on Graphics · doi:10.1145/3528223.3530185 · Cited by 34
Desoiling Dataset: Restoring Soiled Areas on Automotive Fisheye Cameras
Uřičář, M., Uličný, J., Sistu, G., et al. (2019) · doi:10.1109/iccvw.2019.00526 · Cited by 33
“The second column shows our restoration results on our fisheye dataset [14] and the third column shows the ground truth.”
BackgroundMethodInfluentialSelf-citationFisheyeMODNet: Moving Object Detection on Surround-view Cameras for Autonomous Driving
Yahiaoui, M. (2019) · TU Dublin · doi:10.21427/v1ar-t994 · Cited by 41
Self-citationA review of object tracking methods: From general field to autonomous vehicles
Cao, J., Zhang, H., Jin, L., Lv, J., Hou, G., & Zhang, C. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127635 · Cited by 36
Mohamed, E., Ewaisha, M., Siam, M., Rashed, H., Yogamani, S. K., Hamdy, W., El-Dakdouky, M., & El-Sallab, A. (2021) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv48863.2021.9575445 · Cited by 31
Self-citationPanoramic Vision Transformer for Saliency Detection in 360$$^\circ $$ Videos
Yun, H., Lee, S., & Kim, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19833-5_25 · Cited by 36
CarlaScenes: A synthetic dataset for odometry in autonomous driving
Kloukiniotis, A., Papandreou, A., Anagnostopoulos, C., Lalos, A. S., Kapsalas, P., Nguyen, D.-V., & Μουστάκας, Κ. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00498 · Cited by 36
“Moreover, to adapt deep learning algorithms for the fisheye camera, S Yogamani et al generated WoodScape [34] dataset.”
MethodZhang, J., Yang, K., Shi, H., Reiß, S., Peng, K., Ma, C., Fu, H., Torr, P. H. S., Wang, K., & Stiefelhagen, R. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3408642 · Cited by 51
Emotion Recognition Based on Body and Context Fusion in the Wild
Huang, Y., Wen, H., Qing, L., Jin, R., & Xiao, L. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00403 · Cited by 29
“For example, WoodScape[28] was released with original data and a license agreement which enforces the users to strictly adhere to the General Data Protection Regulation(GDPR).”
MethodPanoFlow: Learning 360° Optical Flow for Surrounding Temporal Understanding
Shi, H., Zhou, Y., Yang, K., Yin, X., Wang, Z., Ye, Y., Yin, Z., Shi, M., Li, P., & Wang, K. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3241212 · Cited by 26
“WoodScape [61] comprises of multiple surround-view fisheye”
Dahal, A., Hossen, M. J., Chennupati, S., Sistu, G., Malhan, K., Amasha, M., & Yogamani, S. K. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00287 · Cited by 28
“The dataset will be released as a companion to our recently published dataset [24] to encourage further research in this area.”
MethodSelf-citationSurround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges
Jakab, D., Deegan, B. M., SHARMA, S. K., Grua, E. M., Horgan, J., Ward, E., van de Ven, P. W. J., Scanlan, A., & Eising, C. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3368136 · Cited by 31
“The popular Woodscape datasets [39], [90], examined closely in this paper, use a full fourth-order polynomial model for fisheye projection : Neural networks are not specifically built for distorted images which lead to an expected degrading performance [15].”
BackgroundMethodInfluentialSelf-citationDas, A., Krizek, P., Sistu, G., Burger, F., Madasamy, S., Uricar, M., Kumar, V. R., & Yogamani, S. (2020) · 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294677 · Cited by 25
“A portion of the dataset used will be released publicly as part of our WoodScape dataset [1] to encourage further research.”
MethodSelf-citationMonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation
Heylen, J., Wolf, M. D., Dawagne, B., Proesmans, M., Gool, L. V., Abbeloos, W., Abdelkawy, H., & Reino, D. O. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00108 · Cited by 25
“Figure 7: Qualitative results on unseen camera views: our model predicts 3D boxes on equirectangular fisheye images from [78], though it was never trained for it.”
Survey on Fish-Eye Cameras and Their Applications in Intelligent Vehicles
Qian, Y., Yang, M. Z., & Dolan, J. M. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3210409 · Cited by 23
“Compared to Wood-Scape [19], it provides temporally coherent semantic instance annotations and 3D annotations for 3D reasoning.”
BackgroundMethodImage Analysis in Autonomous Vehicles: A Review of the Latest AI Solutions and Their Comparison
Kozłowski, M., Racewicz, S., & Wierzbicki, S. (2024) · Applied Sciences · doi:10.3390/app14188150 · Cited by 26
OdoViz: A 3D Odometry Visualization and Processing Tool
Ramachandran, S., & McDonald, J. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564712 · Cited by 21
LF-VIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras with Negative Plane
Wang, Z., Yang, K., Shi, H.-W., Li, P., Gao, F., & Wang, K.-W. (2022) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros47612.2022.9981217 · Cited by 24
Robust Data Augmentation and Ensemble Method for Object Detection in Fisheye Camera Images
Duong, V. H., Nguyen, D. Q., Luong, T. V., Vu, H., & Nguyen, T. C. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00695 · Cited by 22
“In 2019, [44] created the Wood-Scape dataset, the first comprehensive dataset for road detection.”
Salient Object Detection in RGB-D Videos
Mou, A., Lu, Y., He, J., Min, D., Fu, K., & Zhao, Q. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3498326 · Cited by 24
“…localization and mapping (SLAM) [44], 3D reconstruction [45], monocular depth estimation [46], object detection [47], object recognition [48], semantic segmentation [49], instance segmentation [50], visual odometry [51], tracking [52], action recognition [53], background subtraction [54], etc .”
BackgroundJaus, A., Yang, K., & Stiefelhagen, R. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3232897 · Cited by 20
Díaz, G. M., Negri, P., & Lencinas, J. D. (2020) · Agricultural and Forest Meteorology · doi:10.1016/j.agrformet.2020.108234 · Cited by 21
Thitisiriwech, K., Panboonyuen, T., Kantavat, P., Iwahori, Y., & Kijsirikul, B. (2022) · IEEE Access · doi:10.1109/access.2022.3176712 · Cited by 19
Multi-Modal Neural Feature Fusion for Automatic Driving Through Perception-Aware Path Planning
Li, Z., Zhou, A., Pu, J., & Yu, J. (2021) · IEEE Access · doi:10.1109/access.2021.3120720 · Cited by 19
“Therefore, many researchers have begun to focus on visual perception methods based on low-cost cameras, all of whom use only a low-cost camera or cameras for performing automatic driving tasks [5], [6], [7], [8].”
BackgroundRotInvMTL: Rotation Invariant MultiNet on Fisheye Images for Autonomous Driving Applications
Arsenali, B., Viswanath, P., & Novosel, J. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00291 · Cited by 19
“A subset of this dataset is described in [33].”
BackgroundAn Online Learning System for Wireless Charging Alignment Using Surround-View Fisheye Cameras
Dahal, A., Kumar, V. R., Yogamani, S. K., & Eising, C. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3182165 · Cited by 20
“The model is trained jointly using the public WoodScape [40] dataset comprising 8k samples and evaluated on 2k samples, augmented by our chargepad data.”
MethodSelf-citationAdversarial Attacks on Multi-task Visual Perception for Autonomous Driving
Sobh, I., Hamed, A., Kumar, V. R., & Yogamani, S. K. (2021) · Journal of Imaging Science and Technology · doi:10.2352/j.imagingsci.technol.2021.65.6.060408 · Cited by 18
“The segmentation task contains seven classes on the WoodScape and employs LovaszSoftmax [2] loss.”
MethodSelf-citationPlayout, C., Ahmad, O. S., Lécué, F., & Farida Cheriet, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.10191 · Cited by 19
“As pointed out by [3], this can be explained by the fact that undistortion causes major issues: a typical fisheye with FoV> 90◦ can not be mapped onto a rectilinear image, leading to a reduction of the FoV in the rectified image.”
Wu, Z., Gan, Y., Li, X., Wu, Y., Wang, X., Xu, T., & Wang, F. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3218594 · Cited by 16
“OmniDet [12] forms an encoder-shared framework with six primary tasks on the fisheye dataset WoodScape [23].”
BackgroundMethodInfluentialPhysics-Informed Guided Disentanglement in Generative Networks
Pizzati, F., Cerri, P., & de Charette, R. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3257486 · Cited by 16
“6, first row. gray →colordirt Here, we rely on the recent fish-eye WoodScape [93] dataset which has some images with soiling on the lens.”
MethodInfluentialFishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation
Shi, H., Li, Y., Yang, K., Zhang, J., Peng, K., Roitberg, A., Ye, Y., Ni, H., Wang, K., & Stiefelhagen, R. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00684 · Cited by 18
Innovating Real Fisheye Image Correction with Dual Diffusion Architecture
Yang, S., Lin, C., Liao, K., & Zhao, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01166 · Cited by 17
“We visualize the correction results of the mainstream methods and our methods on the Woodscape dataset [46].”
MethodGhaziamin, P., Bajaj, K., Bouguila, N., & Patterson, Z. (2024) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc59802.2024.00011 · Cited by 17
“The Woodscape dataset [22] is a fisheye dataset for autonomous vehicles captured by equipped cars with cameras in front of it.”
Method3-D LiDAR and Monocular Camera Calibration: A Review
Zhang, H., Li, S., Zhu, X., Chen, H., & Yao, W. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3530925 · Cited by 19
FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition
Ahmad, O. S., & Lécué, F. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20542 · Cited by 2
RST-MODNet: Real-time Spatio-temporal Moving Object Detection for Autonomous DrivingPreprint
Ramzy, M., Rashed, H., Sallab, A. E., & Yogamani, S. K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00438 · Cited by 16
“Recent automated driving datasets [5] include moving object detection task.”
MethodSelf-citationTao, Y., Muñoz-Bañón, M. Á., Zhang, L., Wang, J., Fu, L. F. T., & Fallon, M. F. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251369905 · Cited by 18
“Other datasets focus on evaluating odometry and SLAM trajectories in the context of autonomous driving, including KITTI (Geiger et al. 2013), Complex Urban (Jeong et al. 2019), and WoodScape (Yogamani et al. 2019).”
IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes
Dokania, S., Hafez, A. H. A., Subramanian, A., Chandraker, M. K., & Jawahar, C. V. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00446 · Cited by 18
“There have been recent works which make use of different sensors such as fisheye lenses to cover a larger area around the ego-vehicle [46, 24] and event camera [33] for training models with faster reaction times.”
BackgroundPGDS-YOLOv8s: An Improved YOLOv8s Model for Object Detection in Fisheye Images
Yang, D., Zhou, J. N., Song, T., Zhang, X., & Song, Y. (2023) · Applied Sciences · doi:10.3390/app14010044 · Cited by 14
SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments
Lee, J.-S., Cho, G., Park, J., Kim, K., Lee, S., Kim, J.-H., Jeong, S.-G., & Joo, K. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00805 · Cited by 16
“We apply a scaled version of the Scale-Invariant (SI) log loss introduced by Eigen et al. [42]: where g i = log ˜ ρ − log ρ with the ground truth depth ρ and predicted depth ˜ ρ .”
MethodOptical flow for autonomous driving: Applications, challenges and improvements
Shen, S., Kerofsky, L. J., & Yogamani, S. K. (2023) · Electronic Imaging · doi:10.2352/ei.2023.35.16.avm-128 · Cited by 16
Self-citationCross-task and time-aware adversarial attack framework for perception of autonomous driving
Lu, Y., Liu, N., Li, Y., Chen, J., & Velipasalar, S. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111652 · Cited by 14
SUPS: A Simulated Underground Parking Scenario Dataset for Autonomous Driving
Hou, J., Chen, Q., Cheng, Y., Chen, G., Xue, X., Zeng, T., & Pu, J. (2022) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc55140.2022.9922031 · Cited by 14
“In such a scenario, narrow roads with obstacles, areas with dazzling or dim lighting, and poor-texture walls increase the noise and uncertainty of sensor measurements To the best of our knowledge, some sequences for SLAM tasks are not open-source yet in WoodScape [5] ∗ Simulated carrier and sensor.”
BackgroundExternal Extrinsic Calibration of Multi-Modal Imaging Sensors: A Review
Liu, Z., Chen, Z., Wei, X., Chen, W., & Wang, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3322229 · Cited by 17
Model-Based Occlusion Disentanglement for Image-to-Image Translation
Pizzati, F., Cerri, P., & de Charette, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58565-5_27 · Cited by 14
“We rely on the recent WoodScape dataset [49] and a simple occlusion model to learn the disentangled representation.”
BackgroundMethodInfluentialBEV-MODNet: Monocular Camera based Bird's Eye View Moving Object Detection for Autonomous Driving
Rashed, H., Essam, M., Mohamed, M., Sallab, A. E., & Yogamani, S. K. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564667 · Cited by 15
“The approach has been evaluated on [27] dataset which provides fisheye images from 4 surroundview cameras and their corresponding MOD annotations captured from real AD scenes.”
MethodSelf-citationPP4AV: A benchmarking Dataset for Privacy-preserving Autonomous Driving
Trinh, L., Pham, P., Trinh, H., Bach, N., Nguyen, D., Nguyen, G., & Nguyen, H. L. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00126 · Cited by 14
“PP4AV provides license plate annotations from the WoodScape dataset [38], a multi-camera fisheye dataset for autonomous driving.”
BackgroundMethodRodrigues, C. N., Nunes, I. M., Pereira, M. B., Oliveira, H., & dos Santos, J. A. (2024) · Computers & Graphics · doi:10.1016/j.cag.2024.104014 · Cited by 15
Gia, B. T., Khanh, T. B. C., Trong, H. H., Doan, T. T., Do, T., Le, D.-D., & Ngo, T. D. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00718 · Cited by 17
Impact of Critical Situations on Autonomous Vehicles and Strategies for Improvement
Beigi, S. A., & Park, B. (2025) · Future Transportation · doi:10.3390/futuretransp5020039 · Cited by 16
Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey
Yu, J., Grassi, A. P., & Hirtz, G. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00683 · Cited by 13
“Depending on the task, these cameras can be mounted with a frontal view, as for example in driving applications [51, 72, 104, 106], with a vertical view as in teleconference applications [70] or with a top view as in surveillance applications [52, 56, 64, 67].”
Improving Gradient Trade-offs between Tasks in Multi-task Text Classification
Chai, H., Cui, J., Wang, Y., Zhang, M., Fang, B., & Liao, Q. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.144 · Cited by 12
Metadata
- Authors
- Yogamani, S., Hughes, C., Horgan, J., Sistu, G., Chennupati, S., Uricar, M., Milz, S., Simon, M., Amende, K., Witt, C., Rashed, H., Nayak, S., Mansoor, S., Varley, P., Perrotton, X., Odea, D., & Perez, P.
- Affiliations
- Valeo (France) (FR)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 9307-9317
- OpenAlex
- W2943449463
- Semantic Scholar
- 57de1a6cc6035d4ac6305121367ad3c6d3fd5104
- Cited by
- 334
- References
- 78
- Citations by year
- 2026: 32 · 2025: 55 · 2024: 61 · 2023: 74 · 2022: 47 · 2021: 40 · 2020: 16 · 2019: 9
- FWCI
- 9.05
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- fisheye camera, surround-view cameras, autonomous driving, semantic segmentation, depth estimation, soiling detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
