The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Improving Multiple Pedestrian Tracking by Track Management and Occlusion Handling
Abstract
Multi-pedestrian trackers perform well when targets are clearly visible making the association task quite easy. However, when heavy occlusions are present, a mechanism to re-identify persons is needed. The common approach is to extract visual features from new detections and compare them with the features of previously found tracks. Since those detections can have substantial overlaps with nearby targets – especially in crowded scenarios – the extracted features are insufficient for a reliable re-identification. In contrast, we propose a novel occlusion handling strategy that explicitly models the relation between occluding and occluded tracks outperforming the feature-based approach, while not depending on a separate re-identification network. Furthermore, we improve the track management of a regression-based method in order to bypass missing detections and to deal with tracks leaving the scene at the border of the image. Finally, we apply our tracker in both temporal directions and merge tracklets belonging to the same target, which further enhances the performance. We demonstrate the effectiveness of our tracking components with ablative experiments and surpass the state-of-the-art methods on the three popular pedestrian tracking benchmarks MOT16, MOT17, and MOT20.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
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
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
High-Speed Tracking with Kernelized Correlation Filters
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2345390 · Cited by 5,753
Simple online and realtime tracking with a deep association metric
Wojke, N., Bewley, A., & Paulus, D. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296962 · Cited by 5,286
Simple online and realtime tracking
Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533003 · Cited by 4,433
Performance Measures and a Data Set for Multi-target, Multi-camera Tracking
Ristani, E., Solera, F., Zou, R., Cucchiara, R., & Tomasi, C. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48881-3_2 · Cited by 3,104
MMDetection: Open MMLab Detection Toolbox and Benchmark
Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et al. (2019) · arXiv · doi:10.48550/arxiv.1906.07155 · Cited by 2,227
Zhou, X., Koltun, V., & Krähenbühl, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58548-8_28 · Cited by 1,428
Flagged first, then by citations
Cited by
Sorted by citations
Items 101–147 of 147
TrackFormer With Prior Position Embedding and Reference Point Updating for Multiple Object Tracking
Liu, X., Pu, K., Ping, Y., Yang, X., Yin, Z., Lan, Z., & Chen, B. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3585134 · Cited by 3
Head Point Positioning and Spatial-Channel Self-Attention Network for Multi-Object Tracking
Zhang, X., Gao, S., Yang, Y., Chu, C., & Zhou, Z. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956665 · Cited by 2
Anomaly Detection in ATM Vestibules Using Three-Stream Deep Learning Approach
Kammakomati, M., Chowdary, S. D., Varthya, S. N., & Seshadri, K. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-31407-0_1 · Cited by 2
HSV-Template Matching With MEESPSO Algorithm for Human Tracking in a Crowded Environment
Fauzi, N. I. H., & Musa, Z. B. (2024) · IEEE Access · doi:10.1109/access.2024.3448242 · Cited by 2
Robust Filtering for Multi-Object Tracking Against Stealthy Measurement-Oriented Adversarial Attacks
Ghorbani, V., Gostar, A. K., Hoseinnezhad, R., Tari, Z., Blair, A., Ghorbani, A., & Battistelli, G. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3697369 · Cited by 2
“MOT has a diverse range of applications, including vehicle tracking and control [4], robotics [5], surveillance[6], computer vision [7], [8], [9] and cell biology [10], [11].”
Joint detection and embedding of multi-object tracking with feature decoupling
Jiang, L., Wang, C., & Yang, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04240-2 · Cited by 2
“Compared with other methods [39], it also achieves a leading advantage.”
Data Association with Graph Network for Multi-Object Tracking
Wu, Y., Sheng, H., Wang, S., Liu, Y., Ke, W., & Xiong, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10983-6_21 · Cited by 2
Towards Large-Scale Video-Based Highway Traffic Monitoring
Spoecklberger, J., Micorek, J., Possegger, H., & Bischof, H. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10421876 · Cited by 1
“[27], [33], [35], follow the same principles, i.e . association between detections and trajectories in a bi-partite graph via the Hungarian algorithm [24] and object state propagation via Kalman filtering [17].”
Autoregressive Temporal Modeling for Advanced Tracking-by-Diffusion
Nguyen, P., Madhok, R., Raj, B., & Luu, K. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02439-x · Cited by 1
“Specific future directions include formulating new object representation (Rajasegaran et al., 2022) and management (Stadler & Beyerer, 2021), motion (Bewley et al., 2016; Wojke et al., 2017), state (M. et al., 2020), temporal displacement (Zhou et al., 2020), camera motion (Aharon et al., 2022;…”
Multi-3D pose tracking based on multi-view fusion feature correlation
Chen, K., Huang, Y., Zhao, X., Fang, G., & Wang, Z. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06774-x · Cited by 1
“In multi-view dynamic tracking, pedestrians often reap-pear after disappearing, presenting significant challenges to most tracking methods [48, 49].”
Dynamic trajectory quantification strategy for multiple object tracking with feature rearrangement
Zhang, Y., Tian, Q., Liu, T., & Kong, J. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.6.063025 · Cited by 1
Liang, J. T. Y., & Kanji, T. (2023) · International Conference on Pattern Recognition Systems (ICPRS) · doi:10.1109/icprs58416.2023.10179060 · Cited by 1
“It should be noted that there are other approaches to traversable region detection [19], such as obstacle detection and floor detection [2] and monocular depth regression [1].”
BackgroundMotion information supplement for joint detection and embedding tracking
Mo, E., Kong, J., Jiang, M., & Liu, T. (2023) · Journal of Electronic Imaging · doi:10.1117/1.jei.32.5.053007 · Cited by 1
A Multiview Approach to Tracking People in Crowded Scenes Using Fusion Feature Correlation
Chen, K., Huang, Y., & Wang, Z. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-7240-1_16 · Cited by 1
Igtracker: task and instance information gaps in multiple object tracking
Liu, J., Kong, J., Jiang, M., & Zhuang, D. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02182-8 · Cited by 1
Multi-object tracking algorithm based on improved TrackFormer
Chen, S., & Ren, X. (2023) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1145/3652628.3652661 · Cited by 1
DFMM: An Object Tracking Approach Based on Deep Feature Modification
Chen, K., Huang, Y., Zhao, X., Wang, Z., & Wang, P. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-7225-4_2 · Cited by 1
DSGA: Distractor-Suppressing Graph Attention for Multi-object Tracking
Gao, G., Gao, Y., Xu, L., Tan, H., & Tang, Y. (2022) · doi:10.1145/3573910.3573916 · Cited by 1
Learning Mutually in Crowd Scenes for Pedestrian Detection
Wei, R., Wang, Y., & Zhang, J. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222019 · Cited by 1
Park, J., Ahn, M. S., & Han, J. (2022) · The Journal of Korea Robotics Society · doi:10.7746/jkros.2022.17.2.124
Improving tracking with a tracklet associator
Nahon, R., Bilodeau, G.-A., & Pesant, G. (2022) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv55824.2022.00030
“still working frame by frame, whether it is with dynamic programming [15] or by going through time in both directions [16] to make their results more robust than they would be online.”
BackgroundHO3-SLAM: Human-Object Occlusion Ordering SLAM Framework for Traversability Prediction
Liang, J. T. Y., & Kanji, T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47634-1_25
Lidar-Based Multiple Object Tracking with Occlusion Handling
Ho, R. C. M., Wang, C., & Lin, W. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342278
“Stadler and Beyerer [17] used only motion cues to re-identify occluded objects.”
MethodMulti-step Ahead Visual Trajectory Prediction for Object Tracking using Echo State Networks
Manibardo, E. L., Laña, I., & Ser, J. D. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422485
“Stadler et al. [16] inherit this idea and focus on handling occlusion by establishing the relationship between occluded and occluding tracks.”
BackgroundApplication of ROI Feature Decomposition and Local Matching in Multi-Object TrackingPreprint
Yang, J., Ban, Y., & Liu, J. (2024) · Research Square · doi:10.21203/rs.3.rs-3951072/v1
Improved Appearance Model for Handling Occlusion in Vehicle Tracking
Mohaideen, A., Dharunsri, Sameer, S., & Brindha, M. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-7820-5_37
Local many-to-many matching via ROI feature decomposition for multi-object tracking
Yang, J., Ban, Y., & Liu, J. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03336-5
Chen, K., Huang, Y., Zhao, X., & Wang, Z. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4891497
A review of pedestrian trajectory tracking based on deep learning
Yu, R., Zhang, Z., Lu, Y., Song, W., Qin, X., Yi, N., & Chen, J. (2024) · International Conference on Image Processing and Artificial Intelligence (ICIPAI) · doi:10.1117/12.3035210
T2Track: Multi-Object Tracking by Associating Between Tracks
Zhang, X., Wang, B., Wei, X., Huang, W., Wang, B., & Sun, C. (2024) · International Conference on Electrical Engineering, Control and Robotics (EECR) · doi:10.1109/eecr60807.2024.10607221
“Method [26] suggests removing a long-term lost track from the track set when it moves outside the image boundary, which inspired us.”
BackgroundTrackFormer++: End-to-End Multi-Object Tracking with Prior Content Information
Pu, K., Chen, T., Liu, X., Zhou, H., & Chen, B. (2024) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec60942.2024.10733034
Selective Frame Analysis for Efficient Object Tracking: Balancing Speed with Accuracy in MOT Systems
Shah, Y. A. R., Guo, Y., Park, L. A. F., & Obst, O. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-0692-4_20
AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation
Zhang, F., Liu, J., Zhu, X., & Chen, L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889872
“Currently, the growing demand for real-time performance has driven researchers to prioritize the development of lightweight models for human pose estimation [1]–[3].”
A Fast Multi-object Tracking Method Based on Geometric Constraints with Occlusion Handling
Shi, Y., Qian, L., Ding, L., & Yang, F. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2468-3_29
LoFSORT: Sample Online and Real-time Tracking in Low Frame Rate Scenarios
Wang, J., & Chang, D. E. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128838
“TMOH [17] introduces the occluding and occluded states of objects and combines them with the two states of the tracker: active and inactive, to handle occlusion between objects.”
Event-Based Vision Sensing and Its Application to Pedestrian Detection for Autonomous DrivingPreprint
Wang, H., Liu, S., Wu, J., Liu, M., Liu, H., Cheng, W., Wang, Y., Zhou, S., Nie, Y., & Li, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5457668
Roleda, J. C., Cruz, A. J., Geronimo, M. R., & Ilao, J. P. (2025) · International Conference on Mechatronics and Machine Vision in Practice (M2VIP) · doi:10.1109/m2vip67511.2025.11165629
“Various works in the field have explored the potential use and feasibility of these systems, extending the applications of single-camera applications in various contexts such as object surveillance and monitoring [10], and pedestrian or crowd analysis [6].”
Li, B., Gong, B., Kong, S., Sun, L., Liu, J., & Gao, D. (2025) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00392-6
Motion and Spatiotemporal Aggregation Network for Occlusion Edge Detection From Videos
Chen, L., Pu, M., Zhihao, L. I. U., Hou, X., Huang, Y., Zhou, R., & Ling, H. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3673936
“It remains a prevalent challenge in various visual understanding tasks, such as semantic segmentation [1], [2], [3], [4], [5], [6], object detection [7], [8], [9], [10], [11], [12], [13], [14], and tracking [15], [16], [17].”
Sentinel for confidence-aware multi-object tracking
Yang, H., Park, S.-W., Sim, C.-B., & Jung, S.-H. (2026) · Scientific Reports · doi:10.1038/s41598-026-43938-2
Mixed self-attention network for multi-object tracking with appearance similarity-guided NMS
Liu, Z., Feng, T., Liu, X., & Zhang, X. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104785
A Real-Time Pedestrian Top-View Tracking System for Multicamera Environment
Choi, J., & Kwon, Y. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454312
“Fusing data from multiple over-lapping camera views in combination with filtering may better resolve ambiguities and maintain robust trajectories [19] [20].”
Inductive Graph Neural Networks for Passive Vision and Acoustic Monitoring
Prummel, W. (2024) · theses.fr (ABES) · doi:10.70675/4949fe39z2d37z4b7dza42cz1d26a43a5401
DTTrack: Metric-Guided Dynamic Template Tracking Network
Liang, Y., Chen, Z., Chen, Y., Chen, Y., Li, D., Liu, W., Wang, C., & Li, J. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3709830
“However, when confronted with challenges such as extreme illumination [1], missing textures [2], or fast-moving targets [3], the single visible modality is often severely constrained by physical sensing bottlenecks.”
Encoder-Level Temporal Fusion Transformers for Robust Multi-Object Tracking
Kim, J., & Yoon, K. (2026) · IEEE Access · doi:10.1109/access.2026.3726723
Bilakeri, S., Manisha, & Akshatha, K. R. (2026) · The Visual Computer · doi:10.1007/s00371-026-04700-x
A multiobject tracking method based on dynamic adaptation and collaborative enhancement
Ji, Y., Guo, Y., Liu, Z., Li, H., Liu, Z., & Fang, H. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07438-0
Metadata
- Authors
- Stadler, D., & Beyerer, J.
- Affiliations
- Karlsruhe Institute of Technology (DE)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 10953-10962
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3175782503
- Cited by
- 147
- References
- 41
- Citations by year
- 2026: 10 · 2025: 22 · 2024: 35 · 2023: 37 · 2022: 39 · 2021: 4
- FWCI
- 9.40
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- multi-pedestrian tracking, occlusion handling, track management, person re-identification, track association, missing detection, crowded scenes
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
