Object Detection in 20 Years: A Survey
Open accessThe DOI matches its Crossref record; 309 of the 309 references it cites were found in a registry or an index; 84 of the 192 sources its claims cite were checked for support.
Abstract
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Over the past two decades, we have seen a rapid technological evolution of object detection and its profound impact on the entire computer vision field. If we consider today’s object detection technique as a revolution driven by deep learning, then, back in the 1990s, we would see the ingenious thinking and long-term perspective design of early computer vision. This article extensively reviews this fast-moving research field in the light of technical evolution, spanning over a quarter-century’s time (from the 1990s to 2022). A number of topics have been covered in this article, including the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speedup techniques, and recent state-of-the-art detection methods.
Overview
CoChat Summary
TL;DR
This survey reviews two decades of object detection research (1990s–2022), tracing the transition from handcrafted-feature detectors to deep-learning-based two-stage, one-stage, and transformer detectors. It organizes the field around milestone detectors, datasets and metrics, key building blocks (multi-scale detection, context, hard negative mining, loss functions, NMS), speed-up techniques, and recent advances.
Key findings
- The field splits into a "traditional object detection period (before 2014)" and a "deep learning based detection period (after 2014)"; RCNN raised VOC07 mAP from 33.7% (DPM-v5) to 58.5%, SPPNet reached VOC07 mAP=59.2% at >20× faster than R-CNN, Fast RCNN reached 70.0% mAP at >200× faster than R-CNN, and Faster RCNN reached COCO mAP@.5=42.7%, VOC07 mAP=73.2% at 17fps.
- One-stage detectors traded some accuracy for speed: YOLO ran at 155fps with VOC07 mAP=52.7% (enhanced version 45fps, 63.4%), SSD reached COCO mAP@.5=46.5% at 59fps, and RetinaNet's focal loss brought one-stage accuracy to COCO mAP@.5=59.1%.
- Keypoint- and transformer-based detectors pushed accuracy further: CornerNet COCO mAP@.5=57.8%, CenterNet 61.1%, and Deformable DETR 71.9% on MS-COCO; the paper notes the top-10 COCO detection methods are all transformer-based.
- Datasets scaled dramatically: VOC07 has 5k train images/12k objects, VOC12 11k/27k, MS-COCO-17 164k images and 897k annotated objects over 80 categories, and Open Images 1,910k images with 15,440k boxes over 600 categories. Evaluation moved from miss-rate vs. FPPW to FPPI, then to AP/mAP, with MS-COCO averaging over IoU thresholds 0.5–0.95.
Methods
- Design: a narrative literature survey spanning roughly a quarter-century (1990s to 2022), structured around technical evolution rather than a systematic/quantitative review protocol.
- Coverage: milestone detectors (VJ, HOG, DPM, RCNN, SPPNet, Fast/Faster RCNN, FPN, YOLO, SSD, RetinaNet, CornerNet, CenterNet, DETR), datasets and metrics, technical building blocks, speed-up techniques, and recent advances (rotation/scale robustness, backbones, localization, segmentation loss, adversarial training, weakly supervised detection, domain adaptation).
- Analysis: qualitative synthesis of reported detector accuracies and speeds, with figures/tables summarizing dataset statistics and accuracy trends; no new experiments are conducted.
Limitations
- The paper states no explicit limitations section; it frames its scope as presenting the evolution of technologies "while neglecting their technical specifics," and notes that the evolution order shown in figures is primarily to assist reader understanding and "may have temporal overlap."
- Evident from the text: as a survey it reports no original experiments or controlled benchmarks, so the cited mAP/speed figures come from the original papers and are not independently verified; the coverage is also selective (milestone detectors and selected recent advances) rather than exhaustive.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
55 Valid · 18 Not valid · 32 Not checked · 50 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“In the deep learning era, due to the increase of computing power, bootstrap was shortly discarded in object detection during 2014-2016 [16-20].”
What the sources say
- Not checked — no full text of the sourcecites [16] matched to “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation” (2014) source
- Disputedcites [17] matched to “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition” (2014) sourceExperimental — accuracy not yet measured
Section 4.1 (page unavailable) says the authors used standard hard negative mining, iterated once, to train their object-detection SVMs. That is contrary to citing this 2014 detector as evidence that bootstrapping had been discarded. The paper does not establish a 2014–2016 trend or attribute one to increased computing power. (LLM, conf=0.78)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [18] matched to “Fast R-CNN” (2015) source
- Partly supportedcites [19] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 (p. 10) says Fast R-CNN abandoned the SVM step that, in SPPnet, used hard-negative mining. This supports a narrower change in one detection system, but not the claim that bootstrapping was discarded across object detection during 2014–2016 or that increased computing power caused the change. (LLM, conf=0.83)
- Could not verifycites [20] matched to “You Only Look Once: Unified, Real-Time Object Detection” (2016) sourceExperimental — accuracy not yet measured
The Introduction (p. 1) contrasts YOLO with earlier detection methods, and Training (p. 3) describes how YOLO is trained. Neither passage addresses whether bootstrapping was discarded in object detection during 2014–2016 or attributes such a change to increased computing power; searches for bootstrapping and hard-negative mining found no passage that does. (LLM, conf=0.72)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Faster RCNN is the first near-realtime deep learning detector (COCO mAP@.5=42.7%, VOC07 mAP=73.2%, 17fps with ZF-Net [48]).”
What the sources say
- Partly supportedcites [19] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 reports 42.7% COCO mAP@0.5; Section 4.1 reports 73.2% VOC 2007 mAP and 17 fps with ZF-Net. These are results from different model configurations: the 73.2% VOC result uses VGG-16, not ZF-Net. The paper describes Faster R-CNN as a fast detector but does not establish that it was the first near-real-time deep-learning detector. (LLM, conf=0.88)
- Partly supportedcites [47] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 reports 42.7% COCO mAP@0.5, and Section 4.1 reports 73.2% VOC 2007 mAP and 17 fps with ZF-Net. The accuracy figures are from VGG-16 experiments, not the 17-fps ZF-Net configuration. The paper describes Faster R-CNN as a fast detector but does not establish that it was the first near-real-time deep-learning detector. (LLM, conf=0.88)
- Partly supportedcites [48] matched to “Visualizing and understanding convolutional networks” (2014) sourceExperimental — accuracy not yet measured
Section 3 (p. 4) describes the authors’ convolutional-network architecture, supporting the citation as an identification of the ZF-Net backbone. The paper does not report Faster R-CNN’s near-real-time status, COCO or VOC07 mAP, or 17-fps speed, so it does not support those performance claims. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In the case of sliding window based detectors, the imbalance between backgrounds and objects could be as extreme as 10 7 :1 [71].”
What the sources say
- Partly supportedcites [71] matched to “What Makes for Effective Detection Proposals?” (2016) sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says sliding-window detection can search 10^6–10^7 windows per image. It does not say that 10^7 of those windows are backgrounds for each object, so it does not establish the claimed 10^7:1 imbalance. (LLM, conf=0.88)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“It achieves state-of-the-art performance on MSCOCO dataset (COCO mAP@.5=71.9%).”
What the sources say
- Supportedcites [43] Zhu, 2020, Deformable DETR: Deformable transformers for end-to-end object detection, arXiv:2010.04159 source
Section 5.3 (pp. 8–9) compares Deformable DETR with state-of-the-art methods on COCO. Its table reports an AP50 of 71.9 for the ResNeXt-101 + DCN configuration with test-time augmentation; the accompanying text reports 52.3 overall AP for that configuration. (LLM, conf=0.91)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Using FPN in a basic Faster R-CNN system, it achieves state-of-the-art single model detection results on the COCO dataset without bells and whistles (COCO mAP@.5=59.1%).”
What the sources say
- Supportedcites [24] matched to “Feature Pyramid Networks for Object Detection” (2017) source
The Introduction describes a state-of-the-art single-model COCO result using FPN with a basic Faster R-CNN detector, without bells and whistles. Section 5.2.3 reports AP@0.5 of 59.1 on COCO test-dev and says the single-model entry surpassed competition winners. Page numbers are not provided in the copy. (LLM, conf=0.94)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
50 more claims · 21 with their cited sources checked
Create a free account to see all 155 claims and to verify the 3 references still open.
- It may state two separate claims as one. 40
- Probably not a substantial claim. 83
- The quote only partly states this claim. 1
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“From navigating through occlusions to efficiently managing scale variations and fine-grained object detection scenarios [9], YOLO faces a myriad of obstacles.”
From YOLOv1 to v8: Unveiling Each Variant–A Comprehensive Review of YOLO (2024) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The speed-up techniques in object detection can be divided into three levels of groups: speed up of 'detection pipeline', 'detector backbone', and 'numerical computation'. , as shown in Fig. 9. Refer to [123] for a more detailed version.”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [123]
The cited source says what the claim attributes to it.
In the citing paper
“The few surveys that mention both object detection and model compression [11] focus on the acceleration of”
From A survey of model compression strategies for object detection (2023) · cites this paper as [11]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In addition to that, most of the reviews in related fields review the object detection model and model compression technology separately, and there is a lack of comprehensive reviews for both.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [11]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ II. OBJECT DETECTION IN 20 YEARS
“Fig. 2: A road map of object detection. Milestone detectors in this figure: VJ Det. [10, 11], HOG Det. [12], DPM [1315], RCNN [16], SPPNet [17], Fast RCNN [18], Faster RCNN [19], YOLO [20-22], SSD [23], FPN [24], Retina-Net [25], CornerNet [26], CenterNet [27], DETR [28].”
§ Object detection accuracy improvements
“CenterNet: X. Zhou et al proposed CenterNet [40] in 2019.”
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 4×
“As the accuracy of a detector depends heavily on its feature extraction networks, in this paper, we refer to the backbone networks, e.g. the ResNet and VGG, as the “engine” of a detector.”
InfluentialImageNet 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 · cited 5×
“In 2012, the world saw the rebirth of convolutional neural networks (CNNs) [35].”
InfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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 · cited 10×
“The main idea of multi-reference detection [19, 22, 23, 41, 47, 51] is to first define a set of references (a.”
InfluentialFaster 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
ImageNet: 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×
“It contains a detection challenge using ImageNet images [61].”
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 3×
“Some well-known detection models of the early time: (a) Eigenfaces [95], (b) Shared weight networks [96], (c) Space displacement networks (Lenet-5) [97], (d) Haar wavelets of VJ detector [10].”
BackgroundMethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 1×
“HOG can be considered as an important improvement of the scale-invariant feature transform [33, 34] and shape contexts [35] of its time.”
BackgroundYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 9×
“L2 loss is prevalent in early research [16], [20], [51], but it is highly affected by outliers and prone to gradient explosion.”
InfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Research works printed but not linked: 9
- 10.5555/3045118.3045336 · doi:10.5555/3045118.3045336
- Girshick, 2023, Discriminatively Trained Deformable Part Models, Release 5
- 10.1109/TPAMI.2016.2577031 · DOI · Paper page
- Krasin, 2017, OpenImages: A Public Dataset for Large-Scale Multi-Label and Multi-Class Image Classification
- Alexe, What is an object, 73
- Müller, When does label smoothing help, 32, 1
- 10.1109/CVPR.2016.308 · DOI · Paper page
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
- 10.1109/ICCV.2017.244 · DOI · Paper page
Cited by
Items 2,201–2,300 of 3,144
Segmentation-based low-resolution spatial tracker for video
Benyamin, M., & Goldman, G. H. (2024) · doi:10.1117/12.3016503
“There are a variety of approaches that incorporate deep learning-based classifiers and tracking algorithms [2].”
Yoon, D., Lee, J., Lee, J., et al. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-61963-2_30
CRDE-net: improved multi-scale detection network for strip steel surface defects based on YOLOV5
Xu, X. X., Wu, J., & Liang, P. (2024) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1117/12.3033573
Research on underwater coral identification method based on deep learning
Xie, X., jiafeng, Z., zhaoxuan, L., et al. (2024) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1117/12.3034149
Automatic Counting Method for Centipedes Based on Deep Learning
Yao, J., Chen, W., Wang, T., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3414114
“Objectdetection technology, as a major research direction in the fields of computer vision and digital image processing in recent years [3], has found broad applications across various industries, including traditional Chinese medicinal materials.”
BackgroundA Novel Approach for Steel Defects Detection Using Yolo-Ae: Iiot Enabled Defect Detection SystemPreprint
Biswas, S., Ganesh, A., & Banerjee, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4866209
Automated classification of olive fruit for enhanced olive oil production using computer vision
Pikoulis, E. V., Blekos, K., & Kosmopoulos, D. (2024) · doi:10.1117/12.3023019
“In recent years, DNN models have contributed significantly to the performance improvement of image-based object detection (see Zou et al 9 ).”
The Computer Vision System for a Crewless Boat
Kramar, V. A., Kramar, O. A., & Alchakov, V. V. (2024) · International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM) · doi:10.1109/icieam60818.2024.10553783
“Object detection using computer vision algorithms is the process of selecting source data from the total mass of heterogeneous objects and classifying them according to characteristic features [10-14].”
MethodDetekcija objekata s pomorskih nadzornih kamera
Pobar, M. (2024) · Politehnika · doi:10.36978/cte.8.1.4
Yan, S., Chang, J., Li, L., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4868687
Perret, T., Dupré, S., Gaillot, A., et al. (2024) · doi:10.25144/22271
Comparative Study of Object Detection Techniques with Deep Convolutional Neural Networks
Khadakkar, O., Khushalani, P., Malik, N., et al. (2024) · International Conference on Innovative Practices in Technology and Management (ICIPTM) · doi:10.1109/iciptm59628.2024.10563686
Small Object Detection Network Based on Attention Mechanism and Feature FusionPreprint
Wang, Y., Huang, X., Xie, G., & Yuan, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4876039
Pengyue, 李. L., Xinying, 续. X., Yandong, 唐. T., et al. (2024) · Infrared and Laser Engineering · doi:10.3788/irla20230538
Sayyad, F. Z., Shallari, I., Mousavirad, S. J., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4886854
Kang, J.-H., Lee, S.-M., & Park, S.-H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4890402
Sscan: Spatial and Semantic Context-Aware Network for Worker Detection at Construction SitePreprint
Xiang, C., Lin, Y., Zhou, B., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4891849
Zhang, X., Ding, Q., Dou, Y., & Ren, S. (2024) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc62350.2024.10588219
“Object detection has been successfully used in autonomous driving, human-computer interaction, and disaster relief [1].”
Panizzon, J. L., Ortoncelli, A. R., Souza, A. C. C., et al. (2024) · doi:10.5753/semish.2024.2994
“Details of the one-and two-step detection algorithms are below [Zou et al. 2023]: • Two-stage algorithms laid the groundwork for object detection algorithms based on Deep Learning.”
MethodMonocular Camera-Based Visual Truck Type RecognitionPreprint
Luo, H., Ye, H., Feng, C., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4900121
Research on monocular vehicle detection and 3D coordinate calculation based on YOLOv7
Xu, Y., Dai, Z., Wu, P., Guo, J., & Wang, W. (2024) · International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT) · doi:10.1117/12.3031154
“Its main content is to detect the position of the object to be measured in the image or video, mark the detection box, and identify the detected object [5] .”
YOLO-ESFM:A Multi-scale YOLO Algorithm for Sea Surface Object Detection.Preprint
Yan, F., Chen, K., Cheng, E., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4623645/v1
Self-citationAircraft Diagnostics Using Convolutional Neural Networks
Mika, D., Jóźwik, J., Tofil, A., et al. (2024) · doi:10.1109/metroaerospace61015.2024.10591556
“CNN is a group of deep feedforward artificial neural networks, normally applied to analyze visual imagery [9], [10], [11], [12].”
BackgroundLIVER ULTRASOUND IMAGING LESION DETECTION BASED ON YOLO
Huang, C.-H. (2024) · International Journal of Engineering Technologies and Management Research · doi:10.29121/ijetmr.v11.i7.2024.1475
Self-Distillated DETR for Object Detection in Complex Environments
Niu, M., Li, F., Huang, Y., et al. (2024) · 2024 IEEE 18th International Conference on Control & Automation (ICCA) · doi:10.1109/icca62789.2024.10591864
“Object detection in complex environments poses a significant challenge [4].”
BackgroundSub-Pixel Feature Alignment Distillation for Low Resolution Detection
Li, J., & Li, X. (2024) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl62147.2024.10603923
“Object detection techniques are mainly divided into two methods: two-stage and one-stage object detection[4].”
MethodRemote sensing small object detection algorithm based on improved YOLOv8
Peng, Y., Qian, J., Tu, S., et al. (2024) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea62105.2024.10603603
“Object detection [1] is a critical technology in the field of remote sensing image processing.”
BackgroundIntelligent Automatic Collection System for Flight Security Nodes at Airports Utilizing GoogleNet
Hou, X., Jin, X. Y., Hu, C., & Zhai, J. (2024) · International Conference on Cryptography, Network Security and Communication Technology (CNSCT) · doi:10.1145/3673277.3673289
“For the target monitoring and identification, the classical CNN has gained comprehensive attention [13].”
One Stage Near-Ground Pothole Object Detection
Li, W., Zhang, X., Lei, Z., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5612-4_36
DDNet: Detection-Focused Dehazing Network
Zhang, B., Tian, W., Zhang, W., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5609-4_13
Integrated Centralized Framework for Industrial Automation
Mishra, S., & Sealy, W. (2024) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit60633.2024.10609943 · Cited by 1
“Zou et al. [16] addresses the need for scalable deployment strategies, including container management, load balancing, and auto-scaling, to support fluctuating data volumes and system demands efficiently.”
BackgroundMethodInfluentialTSNS-YOLO: An Improved Traffic Sign Detection Network for Natural Scenes Based on YOLOv7
Wang, X., & Sun, J. (2024) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai61966.2024.10603378
“Traditional object detection algorithms [2] tend to be computationally intensive and slow, such as VJ Detectors [3], HOG Detector [4], and the Deformable Part-based Model [5].”
BackgroundNikulina, O., Severyn, V. P., Kondratov, O., et al. (2024) · Bulletin of National Technical University KhPI Series System Analysis Control and Information Technologies · doi:10.20998/2079-0023.2024.01.08
Faster-YOLOv5: real-time deep learning for sea cucumber defect recognition and classification
Huang, M., & Wei, H. (2024) · Engineering Research Express · doi:10.1088/2631-8695/ad6af6
Obstacle detection visual slam on improved YOLOv7 for complex environment
Yan, H., Zhou, X., Yin, Z., et al. (2024) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3672758.3672849
Global remote feature modulation end-to-end detection
Bao, X., Yi, W., Tu, X., Zhang, N., Zhang, Q., Jin, Y., & Wu, B. (2024) · Scientific Reports · doi:10.1038/s41598-024-68500-w
Duan, L., Scargill, T., Chen, Y., & Gorlatova, M. A. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610778
Katkoria, D., Sreevalsan‐Nair, J., Sati, M., & Karunakaran, S. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-66705-3_19 · Cited by 1
Performability Modeling and Analysis for Real-Time Object Detection on UAV Systems
Zhang, Q., Machida, F., & Andrade, E. (2024) · IEEE Annual Computers, Software, and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00184
“In recent years, advancements in single-stage detectors have led to their performance in target detection tasks approaching or even surpassing that of two-stage detectors [17] in real-time object detection, such as the YOLO series [18] and Efficient-Det [19].”
BackgroundPatrick, S. R., & Nugroho, R. S. A. (2024) · Proxies Jurnal Informatika · doi:10.24167/proxies.v5i1.12444
“Based on Zou et al. paper [1], object detection is an important computer vision task that deals with detecting instances of visual objects of a certain class (such as humans, animals, or cars) in digital images.”
BackgroundEnd-to-end multitasking network for smart container product positioning and segmentation
Shen, W., & Cai, X. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.5.053009
Coastline Resilience: Leveraging Satellite Imagery and the Co-Detr Model for Storm Damage Assessment
Deng, E. (2024) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss53475.2024.10642784
Exomoon localization in simulations using YOLO
Fernández, A., Cabrera-Vives, G., Donoso-Oliva, C., Zurlo, A., Lazzoni, C., Nogueira, P. H., & Bhowmik, T. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10649926
“A shift in object detection in 2014 is attributed to the role played by deep learning techniques, significantly enhancing the performance of detectors [14].”
BackgroundData-centric AI approach for automated wildflower monitoring
Schouten, G., Michielsen, B. S. H. T., & Gravendeel, B. (2024) · PLoS ONE · doi:10.1371/journal.pone.0302958
“Classifying and localizing multiple wildflowers in overview images is a different, more complex challenge that requires an object detection approach [18].”
BackgroundMulti-Label and Evolvable Dataset Preparation for Web-Based Object Detection
Li, S., Zhu, J., Chang, B., Wu, H., Xu, F., & Zhong, S. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3695465
“Compared with traditional object detection works [4, 9, 10, 20, 36] with their main focus on designing more powerful models, web-based object detection usually places greater emphasis on curating a high-quality dataset for detection model training, due to the uncontrolled nature of web data.”
SDLNet: Statistical Deep Learning Network for Co-Occurring Object Detection and Identification
Singh, B. K., & Lobo, N. D. V. (2024) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1145/3674029.3674055 · Cited by 1
“We have developed a method called SDLNet that can perform co-occurring object detection and prediction.”
Mfdd: Multi-scale attention fatigue and distracted driving detector based on facial features
Shi, Y., Cheng, J., Chen, X., Luo, J., & Tang, X. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01549-y
Real-time defect detection systems for steel and wood inspection
Ghali, R., Benhafid, Z., & Selouani, S. (2024) · Conference proceedings - Canadian Conference on Electrical and Computer Engineering · doi:10.1109/ccece59415.2024.10667164 · Cited by 2
“YOLO models have the advantages of remarkable real-time performance and high precision [9].”
BackgroundIntelligent lead and navigation system for mobile robots combined with multi-sensor data
Yuan, G., Zhang, M., Wei, S., Ma, L., Shen, K., & Sun, Y. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662314
“Traditional object detection algorithms primarily process two-dimensional image data, and most of them are rely on manually constructed features [5].”
BackgroundHazard Detection for Power Transmission Channel Based on Texture Enhancement and Context Awareness
Chen, P., Huang, W.-L., Lin, B., & Liu, P. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10661825
Improved YOLOv8 Viscose Filaments Detection Algorithm Based on Swin Transformer
Xinru, H., Linmin, C., Qing, X., & Ma, L. (2024) · IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) · doi:10.1109/seai62072.2024.10674292
“…Geometry Group (VGG), Single Shot MultiBox Detect (SSD), You Only Look Once (YOLO) and Faster Region-based Convolutional Neural Network (Faster R-CNN) have achieved good results, but these networks have problems such as single detection scale, large computation and large number of parameters[10].”
BackgroundZhang, F., Xiang, X., Zhang, F., & Zhao, J. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-7001-4_1
LRFE-YOLO: Low-Rank Feature Enhancement for YOLO in Few-Shot Industrial Meter Fine Needle Detection
Liu, J., Li, Y., & Chen, Z. (2024) · International Symposium on Computer and Information Processing Technology (ISCIPT) · doi:10.1109/iscipt61983.2024.10673055
“Prior to the advent of deep learning, traditional target detection algorithms for detecting industrial meter faces were based on manual design features [4].”
MethodPink-Eggs Dataset: A Step Toward Invasive Species Management Using Deep Learning Solutions
Hao, X., Xu, D., Zhao, Y., Meng, X., & Wu, J. (2024) · IEEE Conference on Cybernetics and Intelligent Systems · doi:10.1109/cis-ram61939.2024.10672749
Research on Object Detection Algorithm Based on Deep Learning
Zheng, D., & Chen, C. (2024) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai62591.2024.10675004 · Cited by 1
“With the rapid development of computer vision technology, object detection, as one of the core tasks [1-2] , has been widely used in intelligent monitoring [3] , automatic driving [4] , robot vision [5] , medical image analysis [6] and other fields.”
BackgroundOne-Stage Object Detection and Feature Embedding Network for Multiple Object Tracking
Lim, Y. C., & Kang, M. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-2447-5_66
Wang, X., Zhang, Z. B., Jiang, Y., et al. (2024) · Applied Sciences · doi:10.3390/app14198798
Food Recognition and Segmentation Using Detectron2 Framework
Mujagić, A., Mujagić, A., & Mehanović, D. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-71694-2_30 · Cited by 1
Circuit Breaker Defect Detection Based on Deep Learning
陈, 俊. (2024) · Journal of Image and Signal Processing · doi:10.12677/jisp.2024.134032
ODFKG-A: Object Detection Fused with Knowledge Graph Based on Attention Mechanism
Fan, Y., Xu, J., Yang, F., et al. (2024) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat62382.2024.10695313
“In computer vision, object detection technology is crucial for applications like autonomous driving [1] and intelligent security [2-4].”
BackgroundDesign and Implementation of a Mask Wearing Detection System Based on YOLOv5
Zhang, W. (2024) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis63324.2024.10698767
“Mask wearing detection is actually object detection [1] , belonging to a branch of computer vision, mainly divided into two categories: traditional methods and deep learning based methods.”
MethodMetzker, L. F., Araújo, C. C. S., Figueiredo, M. D. M. F., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4978092
An Improved YOLOv8 Network for Detecting UAV Aerial Image
Zhang, B., & Jiang, Z. (2024) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/icnc-fskd64080.2024.10702253
“Object detection networks based on convolutional neural networks can be broadly classified into two categories: two-stage networks that operate based on candidate regions and single-stage networks that directly predict results [2].”
BackgroundDOSDet: A Sequential Feature Enhancement Network for Deck Oil Spill Detection
Zhang, H., Chen, F., An, H., Ma, Y., Zheng, Z., Yue, S., Liu, B., Tong, J., Wang, Y., & Hou, D. (2024) · International Conference on Electronics and Communication, Network and Computer Technology (ECNCT) · doi:10.1109/ecnct63103.2024.10704525
“Zhang D. et al. [2] [3] proposed two levels of context into weakly supervised learning frameworks, resulting in a new deep multiple-instance reasoning framework.”
BackgroundObject Recognition Models for Indoor Users’ Location
Borrelli, F. M., & Challiol, C. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-70807-7_3
“Object recognition and detection have experienced remarkable evolution in the last two decades [8, 10].”
InfluentialGL-YOLO: Pedestrian Detection Algorithm for Small Objects in Long Distances
Abdulatef, M. K., & Zhai, J. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-8650-3_32
Tarafdar, A., Bhattacharya, P., & Bhowmik, C. (2024) · Lecture notes in civil engineering · doi:10.1007/978-981-97-7502-6_24
Learning from Distinction: Mitigating Backdoors Using a Low-Capacity Model
Sun, H., Li, Y., Lv, X., & Ma, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680968
“Deep neural networks (DNNs) have achieved unprecedented success due to their remarkable performance in many applications, such as image classification[41], object detection[63], and traffic accident detection[19, 22].”
BackgroundXu, J., Qinghui, Z., Junqiu, L., et al. (2024) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece61636.2024.10729357
“Currently, there are two prevalent object detection algorithms: two-stage and single-stage [13].”
BackgroundSA-P2T: Sparse Attention-based Pyramid Pooling Transformer Network for Object Detection
Ma, N., Xu, G., Han, Y., & Sun, B. (2024) · IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C) · doi:10.1109/qrs-c63300.2024.00126
“Object detection aims to accurately identify and locate objects of interest from images or videos, which is of great significance for many application scenarios such as self driving, video surveillance, drone detection and intelligent interaction [1] [2] [3] [4] [5] [6] [7].”
BackgroundLightweight Detection Algorithm for Air-to-Ground Threat Object
Xu, X., Liu, B., Zhong, Y. F., & Hua, S. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2872/1/012032
Lightweight Object Detection Based on Autonomous Driving
Hua, S., Wang, P., Li, X., et al. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2872/1/012017
Fine Tuning Panoptic Scene Graph Generation
Hoeronis, I., Trilaksono, B. R., & Utama, N. P. (2024) · International Conference on Computer, Control, Informatics and its Applications · doi:10.1109/ic3ina64086.2024.10732695
“Some issues include precise bounding box localization [12], detection pipeline stages [13], handling multi-scale objects [4], and end-to-end detection processes [14].”
BackgroundLabel-Correlation Adaptive Central Similarity Hashing for Multi-label Image Retrieval
Fu, Y., Wan, Z., Yao, J., & Li, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8692-3_11 · Cited by 3
Improvement Based on CenterNet and Application of Traffic Scenarios
Pan, F., Gao, G., Mao, X., et al. (2023) · IEEE International Conference on Intelligent Transportation Engineering (ICITE) · doi:10.1109/icite59717.2023.10733816
“In this era of intertwined challenges and opportunities, the evolution of traditional target detection algorithms and deep learning has revealed the possibility of continuous innovation for us[1].”
BackgroundLightweight and Efficient Distributed Photovoltaic Panel Defect Detection Model
Gu, Y., & Li, J. (2024) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb63463.2024.10735631
“Over the past few years, the optimization of deep learning algorithms and the development of automated defect detection have shown that Convolutional Neural Networks (CNNs) are effective in detecting defects in PV systems [6].”
BackgroundHilbert-encoded Cooperative Coevolutionary Genetic Algorithm for Few-shot Learning
Zhang, X., Yang, B. O., & Hu, Y. (2024) · International Conference on Machine Intelligence Theory and Applications (MiTA) · doi:10.1109/mita60795.2024.10751691
“Researchers have developed a diverse array of vision models, encompassing tasks such as object detection [1], semantic segmentation [2]-[3], image classification [4] and instance segmentation [5].”
Impact of Image Sensor Input Faults on Pruned Neural Networks for Object Detection
Chen, Y., Zhu, W., Chen, D., Mohammed, O., Khound, P., & Lu, Z. (2024) · Proceedings · doi:10.1109/dft63277.2024.10753547
“Object detection also supports a wide range of applications, including robot vision, autonomous driving, and augmented reality [1], [2].”
Shakirzyanov, R. M., Shleymovich, M. P., & Новикова, С. В. (2023) · Автоматика и телемеханика · doi:10.31857/s0005231023070061
CuesTrack:Multi-Object Tracking Based on Weak Clues and Trajectory Prediction
Zheng, Y. (2024) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca63499.2024.10754464 · Cited by 1
“…algorithms integrated high-performance deep learning object detectors, such as Region-CNN (R-CNN), SSD (Single Shot MultiBox Detector), and YOLO (You Only Look Once) [5], into the detection part of the MOT process, significantly enhancing the performance of online multi-object tracking algorithms.”
Whitecap detection analysis using instance segmentation models
Kim, M.-S., & Seong, J.-H. (2024) · Journal of Advanced Marine Engineering and Technology · doi:10.5916/jamet.2024.48.5.346
Semi-Open Set Object Detection Algorithm Leveraged by Multi-Modal Large Language Models
Wu, K., Wang, Y., He, X., Yan, J., Guo, Y., Jiang, Z., Zhang, X., Wang, W., Xiong, Y., Men, A., et al. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8120175 · Cited by 1
Self-citationScreen Scratch Detection on Credit Card Payment Terminals for Logistics Optimization
Cavalcante, H. L., Alves, D. N. A., Amaral, L., et al. (2024) · doi:10.1109/sbesc65055.2024.10771821
“Over the years, the rapid evolution of deep learning techniques has improved and created many approaches to multiple challenges in object detection [2].”
Efficient Object Detection via Fine-Grained Regularization with Global Initialization
Chen, B., Wu, Q., Chen, S., & Kang, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78122-3_5
Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
Zou, X., Han, K., Zhang, X., Wang, W., & Wu, N. (2024) · Applied Sciences · doi:10.3390/app142311367 · Cited by 2
Zakharov, A. A. (2024) · Программные системы и вычислительные методы · doi:10.7256/2454-0714.2024.4.72558
Borrelli, F. M. (2024) · El Servicio de Difusión de la Creación Intelectual (National University of La Plata) · doi:10.35537/10915/174739
Multi-Task Learning Network Optimization Based on Weight Adaptive
Cao, Z., Li, Y., Ding, C., & Zhang, Z. (2024) · International Conference on Behavioral, Economic, and Socio-Cultural Computing · doi:10.1109/besc64747.2024.10780578 · Cited by 1
“For example, object detection focuses on identifying objects in images and requires defining their contours[5].”
Jiang, Y. L., Wang, F., Li, Y., et al. (2024) · doi:10.1117/12.3045899
“Thus, a scheme of automatic detection 6 or hazardous objects based on current terahertz equipment is desired by staff at the front line.”
Zhou, M., 张, Y. 勇. Z., 栗, J. 剑. L., et al. (2024) · Publications of the Astronomical Society of the Pacific · doi:10.1088/1538-3873/ad95bd
Research Advanced in Object Detection based on Deep Learning
Li, B., Qi, W., & Zhang, X. (2024) · Highlights in Science Engineering and Technology · doi:10.54097/tax5ym24 · Cited by 1
“Additionally, both one-stage and two-stage detectors suffer from significant localization inaccuracies, especially when detecting dense and small objects [17].”
Implementation of presence detection with Haar cascade and local binary patterns histograms
Elkari, B., Ourabah, L., Sekkat, H., Farah, G., Soufi, I., Baddou, A., Hafidi, N., & Moutaouakil, K. E. (2024) · Mathematical Modeling and Computing · doi:10.23939/mmc2024.04.1093 · Cited by 1
Shi, J., & Wang, H. (2024) · International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) · doi:10.1109/iciibms62405.2024.10792772
Wang, J., Zhu, F., Wang, Q., Cui, Y., Sun, H., & Zhao, P. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05993-y
Fish Catch Sorting and Detection Model Improved Based on YOLOv8 Model
Yang, P., Shi, T., Yuan, Y., & Jiang, H. (2024) · Information Technology And Control · doi:10.5755/j01.itc.53.4.38761
A Graph-Based Representation of Wastewater Maps
Miqdadi, I. E., Abouzid, F., Salem Benferhat, A., Chahinian, N., & Delenne, C. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10826095
“With the development of deep learning, new object detection methods in images have emerged [3], achieving high levels of accuracy and efficiency [4].”
Fast Ready-To-Harvest Cotton Detection and Classification with YOLOv8 in Greenhouse Crops
González, G., Martínez, A., Martı́nez, V., et al. (2024) · doi:10.1109/robot61475.2024.10796900
“Computer vision models have more than doubled in accuracy over the past four years [10], enabling the implementation of accurate, flexible, and powerful object detectors.”
Classification of military equipment based on computer vision methods
Basystiuk, O., Rybchak, Z., & Betsa, D. (2024) · Вісник Черкаського державного технологічного університету · doi:10.62660/bcstu/3.2024.21
cao, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5071227
Metadata
- Authors
- Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J.
- Affiliations
- Shanghai Artificial Intelligence Laboratory (CN)
- Carleton University (CA)
- Alibaba Group (China) (CN)
- Venue
- Proceedings of the IEEE
- Published
- 2023-03
- Volume
- 111
- Issue
- 3
- Pages
- 257-276
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W4320002812
- Cited by
- 3,689
- References
- 272
- Citations by year
- 2026: 610 · 2025: 1013 · 2024: 940 · 2023: 541
- FWCI
- 280.65
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62125102)
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, evaluation metrics, deep learning
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (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
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.