RefineNet: Refining Object Detectors for Autonomous Driving
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Highly accurate, camera-based object detection is an essential component of autonomous navigation and assistive technologies. In particular, for on-road applications, localization quality of objects in the image plane is important for accurate distance estimation, safe trajectory prediction, and motion planning. In this paper, wemathematically formulate and study a strategy for improving object localization with a deep convolutional neural network. An iterative region-of-interest pooling framework is proposed for predicting increasingly tight object boxes and addressing limitations in current state-of-the-art deep detection models. The method is shown to significantly improve the performance on a variety of datasets, scene settings, and camera perspectives, producing high-quality object boxes at a minor additional computational expense. Specifically, the architecture achieves impressive gains in performance (up to 6% improvement in detection accuracy) at fast run-time speed (0.22 s per frame on 1242 × 375 sized images). The iterative refinement is shown to impact subsequent vision tasks, such as object tracking in the image plane and in ground plane.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Faster 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
Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics
Bernardin, K., & Stiefelhagen, R. (2008) · EURASIP Journal on Image and Video Processing · doi:10.1155/2008/246309 · Cited by 2,918 · cited 1×
“The methods are sorted by the MOTA metric [42].”
MethodEfficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Lin, G., Shen, C., van den Hengel, A., & Reid, I. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.348 · Cited by 862
Multiple Object Recognition with Visual Attention
Ba, J., Mnih, V., & Kavukcuoglu, K. (2014) · arXiv · doi:10.48550/arxiv.1412.7755 · Cited by 808
Learning to associate: HybridBoosted multi-target tracker for crowded scene
Li, Y., Huang, C., & Nevatia, R. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206735 · Cited by 633
Yang, F., Choi, W., & Lin, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.234 · Cited by 608 · cited 2×
“The studied approach is mathematically formulated on top of R-CNN, and is complementary to most improvements introduced into R-CNN in state-of-the-art detectors (including improved proposals [15], deeper networks [5], or better multi-scale handling [16]).”
MethodVisualizing and Understanding Convolutional Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1311.2901 · Cited by 522
DenseBox: Unifying Landmark Localization with End to End Object Detection
Huang, L., Yang, Y., Deng, Y., & Yu, Y. (2015) · arXiv · doi:10.48550/arxiv.1509.04874 · Cited by 407
RefineNet: Iterative refinement for accurate object localization
Rajaram, R. N., Ohn-Bar, E., & Trivedi, M. M. (2016) · 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2016.7795760 · Cited by 28
Self-citation
Cited by
Deep Learning for Safe Autonomous Driving: Current Challenges and Future Directions
Muhammad, K., Ullah, A., Lloret, J., Ser, J. D., & de Albuquerque, V. H. C. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3032227 · Cited by 659
Chen, Q., Ma, X., Tang, S., Guo, J., Yang, Q., & Fu, S. (2019) · Proceedings of the 4th ACM/IEEE Symposium on Edge Computing · doi:10.1145/3318216.3363300 · Cited by 445
DSNet: Joint Semantic Learning for Object Detection in Inclement Weather Conditions
Huang, S.-C., Le, T.-H., & Jaw, D.-W. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2977911 · Cited by 253
No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles Using Cameras and LiDARs
Rangesh, A., & Trivedi, M. M. (2019) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2019.2938110 · Cited by 158
“detections obtained from three commonly used object detectors [40]–[42].”
MethodSelf-citationA privacy-preserving sensory data sharing scheme in Internet of Vehicles
Kong, Q., Lu, R., Ma, M., & Bao, H. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2017.12.003 · Cited by 85
Metadata
- Authors
- Rajaram, R. N., Ohn-Bar, E., & Trivedi, M. M.
- Venue
- IEEE Transactions on Intelligent Vehicles
- Published
- 2016-12
- Volume
- 1
- Issue
- 4
- Pages
- 358-368
- ISSN
- 2379-8858 (ISSN-L)
- 2379-8904
- OpenAlex
- W2622634896
- Cited by
- 61
- References
- 10
- FWCI
- 3.42
- Type
- journal article
- Language
- en
- Open access
- closed
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.