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
Cited by
Sorted by citations
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking
Cao, J., Pang, J., Weng, X., Khirodkar, R., & Kitani, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00934 · Cited by 1,115
TrackFormer: Multi-Object Tracking with Transformers
Meinhardt, T., Kirillov, A., Leal-Taixe, L., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00864 · Cited by 1,081
Single-Model and Any-Modality for Video Object Tracking
Wu, Z., Zheng, J., Ren, X., Vasluianu, F.-A., Ma, C., Paudel, D. P., Gool, L. V., & Timofte, R. (2024) · 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/cvpr52733.2024.01812 · Cited by 143
“While traditional RGB trackers have shown promise in general settings, they often struggle with challenging scenarios such as occlusions [40, 47], low visibility [83, 92], or fast-moving objects [10, 48].”
BackgroundSimple Cues Lead to a Strong Multi-Object Tracker
Seidenschwarz, J., Brasó, G., Serrano, V. C., Elezi, I., & Leal-Taixé, L. (2023) · 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/cvpr52729.2023.01327 · Cited by 133
“Even new learning-based trackers still rely on motion priors [4,52,63,80] or appearance cues, which may include external reid models [4,63].”
BackgroundRobust Multi-Drone Multi-Target Tracking to Resolve Target Occlusion: A Benchmark
Liu, Z., Shang, Y., Li, T., Chen, G., Wang, Y., Hu, Q., & Zhu, P. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3234822 · Cited by 113
“Apart from that, Limited by the lack of supplementary information, single camera MOT has no advantage to address occlusion circumstances, and some priors predictions are always performed for occlusions [52], [53], [54].”
BackgroundOnline multi-object tracking with unsupervised re-identification learning and occlusion estimation
Liu, Q., Chen, D., Chu, Q., Yuan, L., Liu, B., Zhang, L., & Yu, N. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.01.008 · Cited by 110
“Though great performance has been achieved recently [55, 58, 40, 56, 39], occlusion between objects still remains challenging for MOT.”
BackgroundModelling Ambiguous Assignments for Multi-Person Tracking in Crowds
Stadler, D., & Beyerer, J. (2022) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw54805.2022.00019 · Cited by 106
“Moreover, instead of only extracting information of single objects, some tracking methods also consider the relations between the targets [24, 39, 51].”
BackgroundSelf-citationUTM: A Unified Multiple Object Tracking Model with Identity-Aware Feature Enhancement
You, S., Yao, H., Bao, B., & Xu, C. (2023) · 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/cvpr52729.2023.02095 · Cited by 94
“7 9,676 216,029 1,930 TMOH* [41] Tracktor 62.”
InfluentialLooking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
Zhu, T., Hiller, M., Ehsanpour, M., Ma, R., Drummond, T. W., Reid, I. D., & Rezatofighi, H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3213073 · Cited by 82
“Furthermore, these approaches still rely on conventional post processing steps and heuristics to generate the tracks, and recent gains have mainly been achieved due to specifically tailored components such as hand-designed track management modules [20].”
BackgroundHybrid Motion Model for Multiple Object Tracking in Mobile Devices
Wu, Y., Sheng, H., Zhang, Y., Wang, S., Xiong, Z., & Ke, W. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3219627 · Cited by 71
“Stadler and Beyerer [23] solved the occlusion problem through heuristic trajectory management.”
MethodCow detection and tracking system utilizing multi-feature tracking algorithm
Mar, C. C., Zin, T. T., Tin, P., Honkawa, K., Kobayashi, I., & Horii, Y. (2023) · Scientific Reports · doi:10.1038/s41598-023-44669-4 · Cited by 67
An Occlusion-aware Multi-target Multi-camera Tracking System
Specker, A., Stadler, D., Florin, L., & Beyerer, J. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00471 · Cited by 65
“Our first extension is an occlusion handling strategy that is inspired by the concept of occluded and occluding tracks introduced in [34].”
BackgroundMethodInfluentialSelf-citationA survey of detection-based video multi-object tracking
Dai, Y., Hu, Z., Zhang, S., & Liu, L. (2022) · Displays · doi:10.1016/j.displa.2022.102317 · Cited by 59
MotionTrack: Learning motion predictor for multiple object tracking
Xiao, C., Cao, Q., Zhong, Y., Lan, L., Zhang, X., Luo, Z., & Tao, D. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106539 · Cited by 60
Representing Multimodal Behaviors With Mean Location for Pedestrian Trajectory Prediction
Shi, L., Wang, L., Long, C., Zhou, S., Tang, W., Zheng, N., & Hua, G. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3268110 · Cited by 56
“Liushuai Shi , Le Wang , Senior Member, IEEE , Chengjiang Long , Member, IEEE , Sanping Zhou , Member, IEEE , Wei Tang , Member, IEEE , Nanning Zheng , Fellow, IEEE , and Gang Hua , Fellow, IEEE Abstract —Representing multimodal behaviors is a critical challenge for pedestrian trajectory prediction.”
BackgroundA Multi-Object Tracking Algorithm With Center-Based Feature Extraction and Occlusion Handling
Cao, Z., Li, J., Zhang, D., Zhou, M., & Abusorrah, A. M. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3229978 · Cited by 45
“However, for long-term severe occlusion, these models [15], [16], [17], [18], [19] suffer from low tracking accuracy.”
BackgroundMethodInfluentialBox-Grained Reranking Matching for Multi-Camera Multi-Target Tracking
Yang, X., Ye, J., Lu, J., Gong, C., Jiang, M., Lin, X., Zhang, W., Tan, X., Li, Y., Ye, X., et al. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00349 · Cited by 40
“For further improvement, we perform tracking in both temporal directions similar to [39].”
MethodMulti-Object Tracking and Segmentation Via Neural Message Passing
Brasó, G., Cetintas, O., & Leal-Taixé, L. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01678-6 · Cited by 39
“Regression-based methods, instead, have the ability to track an increased number of boxes, and hence can improve MOTA significantly, but fall short in terms of data association performance, as can be seen from the relatively lower IDF1 scores of CenterTrack (Zhou et al., 2020) and TMOH (Stadler & Beyerer, 2021).”
InfluentialLiu, Y., Dong, X., Lin, Y., Ye, M., Zhang, K., & Du, B. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3645918 · Cited by 43
Object Detection, Recognition, and Tracking Algorithms for ADASs—A Study on Recent Trends
Shivanna, V. M., & Guo, J.-I. (2023) · Sensors · doi:10.3390/s24010249 · Cited by 40
Multi-Pedestrian Tracking with Clusters
Stadler, D., & Beyerer, J. (2021) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss52988.2021.9663829 · Cited by 31
Self-citationMultiple Pedestrian Tracking Under Occlusion: A Survey and Outlook
Sun, Z., Wei, G., Fu, W. E., Ye, M., Jiang, K., Liang, C., Zhu, T., He, T., & Mukherjee, M. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3481425 · Cited by 35
Improving Multi-Target Multi-Camera Tracking by Track Refinement and Completion
Specker, A., Florin, L., Cormier, M., & Beyerer, J. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00361 · Cited by 27
“To reduce the negative impact of such situations, we perform single-camera tracking in both temporal directions [48].”
MethodSelf-citationTrack initialization and re-identification for 3D multi-view multi-object tracking
Van, L. N., Nguyen, T. T. D., Vo, B., Jang, H., & Jeon, M. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102496 · Cited by 29
“A popular approach is to use designated modules that analyze occlusion, using object depth [48], or spatial information of objects and their interactions to resolve occlusion [49], [50].”
BackgroundOn the Performance of Crowd-Specific Detectors in Multi-Pedestrian Tracking
Stadler, D., & Beyerer, J. (2021) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss52988.2021.9663836 · Cited by 26
Self-citationLMOT: Efficient Light-Weight Detection and Tracking in Crowds
Mostafa, R., Baraka, H., & Bayoumi, A. (2022) · IEEE Access · doi:10.1109/access.2022.3197157 · Cited by 26
Online multi-object tracking with δ-GLMB filter based on occlusion and identity switch handling
Abbaspour, M., & Masnadi‐Shirazi, M. A. (2022) · Image and Vision Computing · doi:10.1016/j.imavis.2022.104553 · Cited by 28
NCT:noise-control multi-object tracking
Zeng, K., You, Y., Shen, T., Wang, Q., Tao, Z., Wang, Z., & Liu, Q. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00946-9 · Cited by 25
“Figure 11 shows the visual comparison with previous state-of-the-art methods, including MAT [15], TransCtr [54], and TMOH [47] in frame 100, frame 200, and frame 450 of MOT17-01.”
MethodInfluentialFusion detection and ReID embedding with hybrid attention for multi-object tracking
Chan, S., Qiu, C., Wu, D., Hu, J., Heidari, A. A., & Chen, H. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127328 · Cited by 23
SCTracker: Multi-Object Tracking With Shape and Confidence Constraints
Mao, H., Chen, Y., Li, Z., Chen, P., & Chen, F. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3339212 · Cited by 23
BYTEv2: Associating More Detection Boxes Under Occlusion for Improved Multi-person Tracking
Stadler, D., & Beyerer, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-37660-3_6 · Cited by 22
Self-citationDistributed multi-camera multi-target association for real-time tracking
Yang, S.-Q., Ding, F., Li, P., & Hu, S.-X. (2022) · Scientific Reports · doi:10.1038/s41598-022-15000-4 · Cited by 22
“This problem can be dealt with by learning and updating the appearance of targets using a track management 32 or a person re-identification dataset 33 .”
BackgroundAOH: Online Multiple Object Tracking With Adaptive Occlusion Handling
Jiang, M., Zhou, C., & Kong, J. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3191549 · Cited by 21
Tracking Game: Self-adaptative Agent based Multi-object Tracking
Wang, S., Yang, D., Wu, Y., Liu, Y., & Sheng, H. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548231 · Cited by 21
Pixel-Guided Association for Multi-Object Tracking
Boragule, A., Jang, H., Ha, N., & Jeon, M. (2022) · Sensors · doi:10.3390/s22228922 · Cited by 19
Design of public open space: Site features, playing, and physical activity
Loo, B. P. Y., & Zhang, F. (2023) · Health & Place · doi:10.1016/j.healthplace.2023.103149 · Cited by 20
Center-point-pair detection and context-aware re-identification for end-to-end multi-object tracking
Zhang, X., Ling, Y., Yang, Y., Chu, C., & Zhou, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.11.094 · Cited by 19
Tracking Passengers and Baggage Items Using Multiple Overhead Cameras at Security Checkpoints
Siddique, A., & Medeiros, H. P. (2022) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2022.3225252 · Cited by 22
“Single-camera trackers [8], [58] use detectors trained on multiple datasets [59] to generate bounding boxes and form track hypotheses for all the targets in each frame.”
BackgroundSTMT: Spatio-temporal memory transformer for multi-object tracking
Gu, S., Ma, J., Hui, G., Xiao, Q., & Shi, W. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04617-1 · Cited by 17
Multi-Camera Multi-Person Tracking and Re-Identification in an Operating Room
Hu, H., Hachiuma, R., Saitô, H., Takatsume, Y., & Kajita, H. (2022) · Journal of Imaging · doi:10.3390/jimaging8080219 · Cited by 16
“The pedestrian tracking problem has been a popular research field since it was proposed [19,20].”
BackgroundExploring the social life of urban spaces through AI
Miranda, A. S., Fan, Z., Baick, M., Hampton, K. N., Duarte, F., Loo, B. P. Y., Glaeser, E. L., & Ratti, C. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2424662122 · Cited by 15
Enhancing Pedestrian Tracking in Autonomous Vehicles by Using Advanced Deep Learning Techniques
Sukkar, M., Shukla, M., Kumar, D., Gerogiannis, V. C., Kanavos, A., & Acharya, B. (2024) · Information · doi:10.3390/info15020104 · Cited by 16
“In [21], an occlusion handling strategy for a multi-pedestrian tracker is proposed, capable of retrieving targets without the need for re-identification models.”
ORT: Occlusion-robust for multi-object tracking
Han, S., Wang, H., Yu, E., & Hu, Z. (2023) · Fundamental Research · doi:10.1016/j.fmre.2023.02.003 · Cited by 14
“We follow the concept in TMOH [16] , namely if A occludes B, we call A is 𝑜𝑐 𝑐 𝑙𝑢𝑑𝑖𝑛𝑔 and B is 𝑜𝑐 𝑐 𝑙𝑢𝑑 𝑒𝑑 .”
SSL-MOT: self-supervised learning based multi-object tracking
Kim, S., Lee, J., & Ko, B. C. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03473-9 · Cited by 13
“As shown in Table 6, although TMOH showed the best performance among the online MOT methods, this method also uses a refinement of public detection such as CenterTrack and has a disadvantage in that the processing speed is extremely low at 0.6 Hz.”
MethodInfluentialBGTracker: Cross-Task Bidirectional Guidance Strategy for Multiple Object Tracking
Zhou, C., Jiang, M., & Kong, J. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3256761 · Cited by 14
Zhao, T., Yang, G., Li, Y., Lu, M., & Sun, H. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105303 · Cited by 13
Nagy, M., Khonji, M., Dias, J. M. M., & Javed, S. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160328 · Cited by 13
FollowMe: a Robust Person Following Framework Based on Visual Re-Identification and Gestures
Rollo, F., Zunino, A., Raiola, G., Amadio, F., Ajoudani, A., & Tsagarakis, N. (2023) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso56563.2023.10187536 · Cited by 12
“TMOT [22] performs human tracking in cluttered and occluded environments but the time performance is not satisfactory for our goal (See Sect.”
BackgroundTowards pedestrian head tracking: A benchmark dataset and a multi-source data fusion network
Sun, K., Wang, X., Liu, S., Zhao, Q., Huang, G., & Liu, C. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111265 · Cited by 12
Qiu, Y., Nagasaki, Y., Hara, K., Kataoka, H., Suzuki, R., Iwata, K., & Satoh, Y. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00335 · Cited by 11
DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions
Fu, T., Wang, X., Yu, H., Niu, K., Li, B., & Xue, X. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611728 · Cited by 11
“While using ReID information to match reappearing objects is a common method to handle occlusion [58], it does not work well for scenarios where the object is often locally invisible [13].”
MethodA systematic survey on recent deep learning-based approaches to multi-object tracking
Agrawal, H., Halder, A., & Chattopadhyay, P. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16910-9 · Cited by 12
Cross-modality feature fusion for night pedestrian detection
Feng, Y., Luo, E., Lu, H., & Zhai, S. (2024) · Frontiers in Physics · doi:10.3389/fphy.2024.1356248 · Cited by 11
Prototype-guided Instance matching for multiple pedestrian tracking
Wang, Q., Zhang, W., Yang, W., Xu, C., & Cui, Z. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.03.068 · Cited by 10
APPTracker: Improving Tracking Multiple Objects in Low-Frame-Rate Videos
Zhou, T., Luo, W., Shi, Z., Chen, J., & Ye, Q. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548162 · Cited by 10
“With the development of multi-object trackers, recent works [2, 31, 33, 36, 46, 47] start to focus on tracking multiple objects in challenging scenarios.”
BackgroundMulti-object Tracking with Spatial-Temporal Tracklet Association
You, S., Yao, H., Bao, B., & Xu, C. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3635155 · Cited by 9
A hybrid approach to real-time multi-target tracking
Scarrica, V. M., Panariello, C., Ferone, A., & Staiano, A. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09799-4 · Cited by 11
SSAT: Self-Supervised Associating Network for Multiobject Tracking
Chung, T.-Y., Cho, M., Lee, H.-S., & Lee, S. (2022) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2022.3186751 · Cited by 10
“Recent studies have improved performance immensely by focusing on mitigating occlusion in various ways [20] or continuously estimating the occluded object [21].”
BackgroundLabel-based Multiple Object Ensemble Tracking with Randomized Frame Dropping
Kawanishi, Y. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956158 · Cited by 9
Framework for Generation and Removal of Multiple Types of Adverse Weather from Driving Scene Images
Yang, H., Carballo, A., Zhang, Y., & Takeda, K. (2023) · Sensors · doi:10.3390/s23031548 · Cited by 9
An Efficient Multi-Object Tracking Guided by Spatial Clustering on Vision Sensors
Chen, Y. H., Li, Z., Wu, L., & Chen, P. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3391510 · Cited by 8
“…MOT algorithms can be categorized into three types: MOT with separate detection and tracking [13], [14], [15], [16], [17], [18], MOT with joint detection and appearance representation [4], [19], [20], [21], and end-to-end MOT with joint detection and tracking [8], [22], [23], [24], [25], [26].”
BackgroundMethodMulti-object tracking by multi-feature fusion to associate all detected boxes
Bilakeri, S., & Karunakar, A. K. (2022) · Cogent Engineering · doi:10.1080/23311916.2022.2151553 · Cited by 8
“In comparison with the top three best-performing trackers (MPTC (Hornakova et al., 2020), Transctr (Xu et al., 2021), TMOH (Stadler & Beyerer, 2021a)), our method improved the MOTA by 8.4%, IDF1 by 6.4%, and the number of ID switches reduced to 1908.”
MethodInfluentialG2EMOT: Guided Embedding Enhancement for Multiple Object Tracking in Complex Scenes
Ma, J., Wu, F., Li, C., Tang, C., Zhang, J., Xu, Z., Li, M., & Liu, D. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3449952 · Cited by 8
“Therefore, some works [26], [27], [28], [29] incorporated object appearance embeddings to mitigate IDS and object occlusion during long-term tracking.”
BackgroundMulti-object tracking based on network flow model and ORB feature
Chen, J., Xi, Z., Lu, J., & Ji, J. (2022) · Applied Intelligence · doi:10.1007/s10489-021-03042-6 · Cited by 8
“Lif [81] and TMOH [45] have a better MOTA score in MOT2016-01 and MOT16-03, respectively.”
BackgroundMethodA review of object tracking based on deep learning
Zhao, G., Meng, F., Yang, C., Wei, H., Zhang, D., & Zheng, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130988 · Cited by 7
Robust ensemble person reidentification via orthogonal fusion with occlusion handling
Ferdous, S. N., & Li, X. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105010 · Cited by 7
OffsetNet: Towards Efficient Multiple Object Tracking, Detection, and Segmentation
Zhang, W., Li, J., Xia, M., Gao, X., Tan, X., Shi, Y., Huang, Z., & Li, G. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3485644 · Cited by 9
Group Guided Data Association for Multiple Object Tracking
Wu, Y., Sheng, H., Wang, S., Liu, Y., Xiong, Z., & Ke, W. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26293-7_29 · Cited by 7
Learning from Outputs: Improving Multi-Object Tracking Performance by Tracker Fusion
Scarrica, V. M., & Staiano, A. (2024) · Technologies · doi:10.3390/technologies12120239 · Cited by 7
ConsistencyTrack: A robust multi-object tracker with a generation strategy of consistency model
Jiang, L., Wang, Z., Yin, S., Ma, G., Zhang, P., & Wu, B. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112225 · Cited by 7
Similarity- and Quality-Guided Relation Learning for Joint Detection and Tracking
Feng, W., Bai, L., Yao, Y., Gan, W., Wu, W., & Ouyang, W. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3279670 · Cited by 6
Prasannakumar, A., & Mishra, D. (2024) · Journal of Imaging · doi:10.3390/jimaging10070171 · Cited by 6
OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking
Gao, J., Wang, Y., Yap, K., Garg, K., & Han, B. S. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3565334 · Cited by 7
An Effectively Finite-Tailed Updating for Multiple Object Tracking in Crowd Scenes
Xu, B., Liang, D., Li, L., Quan, R., & Zhang, M. (2022) · Applied Sciences · doi:10.3390/app12031061 · Cited by 6
Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning
Yoo, Y., Lee, S.-H., & Bae, S. (2022) · Sensors · doi:10.3390/s22207943 · Cited by 9
“[2,28,61] exploit the Faster RCNN head [62] which is one of popular detection methods.”
MethodInference-Domain Network Evolution: A New Perspective for One-Shot Multi-Object Tracking
Li, R., Zhang, B., Liu, J., Liu, W., & Teng, Z. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3263104 · Cited by 6
Shi, W., Tran, P. T. M., Celedón‐Pattichis, S., & Pattichis, M. S. (2024) · IEEE Access · doi:10.1109/access.2024.3387932 · Cited by 8
“More recently, a geometric approach has been developed in [5] and [6].”
BackgroundMethodOsaMOT: Occlusion and scale‐aware multi‐object tracking algorithm for low viewpoint
Yue, Y., Xu, D., He, K., Shi, H., & Zhang, H. (2021) · IET Image Processing · doi:10.1049/ipr2.12378 · Cited by 6
Clustertracker: An Efficiency-Focused Multiple Object Tracking MethodPreprint
Lohn-Jaramillo, J., RAY, L. R., Granger, R., & Bowen, E. F. W. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4102945 · Cited by 6
Re-identification assistance and multi-stage association for pedestrian multi-object tracking
Li, Y., Li, Z., Wu, L., Liu, H., Min, J., & Wang, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-07276-z · Cited by 5
HCgNet: A hierarchical context-guided network for multi-object tracking
Li, R., Zhang, B., Liu, W., Li, Z., Fan, J., Teng, Z., & Jianping Fan, B. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111859 · Cited by 5
Jiang, Y., Ding, W., Li, H., & Chi, Z. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3405339 · Cited by 7
“Multi-Object Tracking (MOT) is the task of detecting objects from video frames and maintaining consistent instance IDs across frames [22], [32], [33].”
BackgroundJoint Object Detection and Multi-Object Tracking Based on Hypergraph Matching
Cui, Z., Dai, Y., Duan, Y., & Tao, X. (2024) · Applied Sciences · doi:10.3390/app142311098 · Cited by 5
Improving multi‐object tracking by full occlusion handle and adaptive feature fusion
Yue, Y., Yang, Y., Yu, Y., & Liu, H. (2023) · IET Image Processing · doi:10.1049/ipr2.12874 · Cited by 5
BiTrack: Bidirectional Offline 3D Multi-Object Tracking Using Camera-LiDAR Data
Huang, K., Chen, Y., Zhang, M., & Hao, Q. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128796 · Cited by 5
“ReMOT [9] uses a sliding window to re-evaluate 2D object similarities for tracklet split-merge, while TMOH [10] assembles forward and backward sequences, addressing object link contradictions by replacing the entire trajectory.”
AMtrack: Anti-occlusion multi-object tracking algorithm
Liu, Z., Huang, X., Sun, J., & Zhang, X. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03547-w · Cited by 4
Depth Perspective-Aware Multiple Object Tracking
Quach, K. G., Nguyen, P., Duong, C. N., Bui, T. D., & Luu, K. (2024) · Springer tracts in nature-inspired computing · doi:10.1007/978-981-97-5979-8_9 · Cited by 4
Multi-object tracking with robust object regression and association
Li, Y., Ji, H., Chen, X., Lai, Y., & Yang, Y. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103586 · Cited by 4
“Besides, as shown in Table 7, our method runs faster than TMOH because of fewer computation burdens.”
BackgroundMethodInfluentialLearning key lines for multi-object tracking
Li, Y., Ji, H., Chen, X., Yang, Y., & Lai, Y. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.103973 · Cited by 4
“An occlusion handling strategy is proposed in TMOH (Stadler and Beyerer, 2021) that models the occluding and occluded tracks to improve box-based identity management.”
Joint Re-Detection and Re-Identification for Multi-Object Tracking
He, J. Y., Zhong, X., Yuan, J., Tan, M., Zhao, S., & Zhong, L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98358-1_29 · Cited by 4
MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
Pedersen, M., Haurum, J. B., Dendorfer, P., & Moeslund, T. B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20074-8_2 · Cited by 5
Triyanto, W. A., Adi, K., & Suseno, J. E. (2024) · Mathematical Modelling and Engineering Problems · doi:10.18280/mmep.110227 · Cited by 4
Shi, L., Wang, L., Zhou, S., Tang, W., & Hua, G. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3626815 · Cited by 3
Online visual multi-object tracking via blind super-resolution and clustering learning
Sun, Z., Lv, Z., Xiong, M., Hu, W., Wei, G., Zhou, J., He, T., & Meng, Q. (2026) · The Visual Computer · doi:10.1007/s00371-026-04382-5 · Cited by 3
“Thirteen state-of-the-art trackers have been selected to compare their performance with that of our tracker on the MOT20 dataset in this work: TMOH [48], Aplift [50], TBC [65], LPC [66], MeMOT [56], OUTrack [55], IQHAT [54], SDOF [67], SCAUT [68], SUSHI [69], SSMOT [71], DTrack [72], and TADN [70].”
RTAT: A Robust Two-Stage Association Tracker for Multi-object Tracking
Guo, S. S., Liu, R., & Abe, N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78444-6_28 · Cited by 3
Occlusion-Robust Multi-Target Tracking and Segmentation Framework with Mask Enhancement
Sheng, H., Zhang, D., Yang, D., Yang, D., Xi, L., & Ke, W. (2025) · Applied Sciences · doi:10.3390/app15136969 · Cited by 3
EOD-EMDA: A method for automatically identifying and tracking individual pigs in herds
Li, W., Yuan, H., Zhu, X., & Yang, X. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101259 · Cited by 3
Tracking Pedestrians Under Occlusion in Parking Space
Zhou, Z., Yamada, S., Watanabe, Y., & Takada, H. (2022) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.029005 · Cited by 3
Wang, Z., Peng, P., Geng, K., Cheng, X., Zhu, X., Chen, J., & Yin, G. (2023) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2023.129350 · Cited by 3
Interaction-Aware Labeled Multi-Bernoulli Filter with Road Constraints
Ishtiaq, N., Gostar, A. K., Bab‐Hadiashar, A., Palmer, J. L., & Hoseinnezhad, R. (2022) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais56082.2022.9990395 · Cited by 3
“surveillance [1]–[3], people tracking [4], [5], track-beforedetect visual tracking applications [6], sensor management in target tracking applications [7], [8] and information fusion [9], animal [10]–[12] and insect tracking [13]–[15], vehicle track-”
Background
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
