Dynamic Collaborative Optimization Method for Real-Time Multi-Object Tracking
Source abstract
Abstract
Multi-object tracking still faces significant challenges in complex conditions such as dense scenes, occlusion environments, and non-linear motion, especially regarding the detection and identity maintenance of small objects. To tackle these issues, this paper proposes a multi-modal fusion tracking framework that realizes high-precision tracking in complex scenarios by collaboratively optimizing feature enhancement and motion prediction. Firstly, a multi-scale feature adaptive enhancement (MS-FAE) module is designed, integrating multi-level features and introducing a small object adaptive attention mechanism to enhance the representation ability for small objects. Secondly, a cross-frame feature association module (CFAM) is put forward, constructing a global semantic association network via grouped cross-attention and a memory recall mechanism to solve the matching difficulties in occlusion and dense scenes. Thirdly, a Dynamic Motion Model (DMM) is developed, enabling the robust prediction of non-linear motion based on an improved Kalman filter framework. Finally, a Bi-modal dynamic decision method (BDDM) is devised to fuse appearance and motion information for hierarchical decision making. Experiments conducted on multiple public datasets, including MOT17, MOT20, and VisDrone-MOT, demonstrate that this method remarkably improves tracking accuracy while maintaining real-time performance. On the MOT17 test set, it achieves 63.7% in HOTA, 61.4 FPS in processing speed, and 79.4% in IDF1, outperforming current state-of-the-art tracking algorithms.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotic Path Planning Algorithms · Video Surveillance and Tracking Methods · Robotics and Sensor-Based Localization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation and Intelligence, Beijing Jiaotong University, Beijing 100044, China
References (38)
Show source-provided references
1. A Review of Multi-Object Tracking in Recent Times10.1049/cvi2.70010 ↗
2. Solano-Carrillo, E., Sattler, F., Alex, A., Klein, A., Costa, B.P., Rodriguez, A.B., and Stoppe, J. (2024). UTrack: Multi-Object Tracking with Uncertain Detections. arXiv.
3. Cai, J., Xu, M., Li, W., Xiong, Y., Xia, W., Tu, Z., and Soatto, S. (2022, January 18–24). Memot: Multi-object tracking with memory. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00792 ↗
4. Huang, C., Han, S., He, M., Zheng, W., and Wei, Y. (2024, January 16–22). DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.01825 ↗
5. Xiao, C., Cao, Q., Luo, Z., and Lan, L. (November, January 28). Mambatrack: A simple baseline for multiple object tracking with state space model. Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, VIC, Australia.
6. Fan, H., Du, D., Wen, L., Zhu, P., Hu, Q., Ling, H., Shah, M., Pan, J., Schumann, A., and Dong, B. (2020). Visdrone-mot2020: The vision meets drone multiple object tracking challenge results. Computer Vision–ECCV 2020 Workshops: Glasgow, UK, 23–28 August 2020, Springer International Publishing. Proceedings, Part IV 16.10.1007/978-3-030-66823-5_43 ↗
7. Veeramani, B., Raymond, J.W., and Chanda, P. (2018). DeepSort: Deep convolutional networks for sorting haploid maize seeds. BMC Bioinform., 19.10.1186/s12859-018-2267-2 ↗
8. Wojke, N., Bewley, A., and Paulus, D. (2017, January 17–20). Simple online and realtime tracking with a deep association metric. Proceedings of the 2017 IEEE International Conference on Image Processing, Beijing, China.10.1109/ICIP.2017.8296962 ↗
9. Özcan, İ., Altun, Y., and Parlak, C. (2024). Improving YOLO detection performance of autonomous vehicles in adverse weather conditions using metaheuristic algorithms. Appl. Sci., 14.10.3390/app14135841 ↗
10. Park, S., Kim, J., Wang, S., and Kim, J. (2025). Effectiveness of Image Augmentation Techniques on Non-Protective Personal Equipment Detection Using YOLOv8. Appl. Sci., 15.10.3390/app15052631 ↗
11. Eum, I., Kim, J., Wang, S., and Kim, J. (2025). Heavy Equipment Detection on Construction Sites Using You Only Look Once (YOLO-Version 10) with Transformer Architectures. Appl. Sci., 15.10.3390/app15052320 ↗
12. Lu, Z., Han, B., Dong, L., and Zhang, J. (2024). COTTON-YOLO: Enhancing Cotton Boll Detection and Counting in Complex Environmental Conditions Using an Advanced YOLO Model. Appl. Sci., 14.10.3390/app14156650 ↗
13. Ghiasi, G., Lin, T.Y., and Le, Q.V. (2019, January 15–20). Nas-fpn: Learning scalable feature pyramid architecture for object detection. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00720 ↗
14. Wang, K., Liew, J.H., Zou, Y., Zhou, D., and Feng, J. (November, January 27). Panet: Few-shot image semantic segmentation with prototype alignment. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00929 ↗
15. ASPP: A new family of oncogenes and tumour suppressor genes10.1038/sj.bjc.6603525 ↗
16. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
17. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13–19). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
18. Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., and Wang, X. (2022). Bytetrack: Multi-object tracking by associating every detection box. European Conference on Computer Vision, Springer.10.1007/978-3-031-20047-2_1 ↗
19. Strongsort: Make deepsort great again10.1109/TMM.2023.3240881 ↗
20. Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., and Luo, P. (2020). Transtrack: Multiple object tracking with transformer. arXiv.
21. Chu, P., Wang, J., You, Q., Ling, H., and Liu, Z. (2023, January 2–7). Transmot: Spatial-temporal graph transformer for multiple object tracking. Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.10.1109/WACV56688.2023.00485 ↗
22. Cao, J., Pang, J., Weng, X., Khirodkar, R., and Kitani, K. (2023, January 11–15). Observation-centric sort: Rethinking sort for robust multi-object tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR52729.2023.00934 ↗
23. Aharon, N., Orfaig, R., and Bobrovsky, B.Z. (2022). Bot-sort: Robust associations multi-pedestrian tracking. arXiv.
24. Wang, C.Y., Yeh, I.H., and Mark Liao, H.Y. (2024). Yolov9: Learning what you want to learn using programmable gradient information. European Conference on Computer Vision, Springer.10.1007/978-3-031-72751-1_1 ↗
25. Welch, G., and Bishop, G. (1995). An Introduction to the Kalman Filter, University of North Carolina.
26. Milan, A., Leal-Taixé, L., Reid, I., Roth, S., and Schindler, K. (2016). MOT16: A benchmark for multi-object tracking. arXiv.
27. Dendorfer, P., Rezatofighi, H., Milan, A., Shi, J., Cremers, D., Reid, I., Roth, S., Schindler, K., and Leal-Taixé, L. (2020). Mot20: A benchmark for multi object tracking in crowded scenes. arXiv.
28. Wen, L., Zhu, P., Du, D., Bian, X., Ling, H., Hu, Q., Zheng, J., Peng, T., Wang, X., and Zhang, Y. (2019, January 27–28). Visdrone-mot2019: The vision meets drone multiple object tracking challenge results. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, Seoul, Republic of Korea.10.1109/ICCVW.2019.00028 ↗
29. Evaluating multiple object tracking performance: The clear mot metrics10.1155/2008/246309 ↗
30. Fairmot: On the fairness of detection and re-identification in multiple object tracking10.1007/s11263-021-01513-4 ↗
31. Corr-track: Category-level 6d pose tracking with soft-correspondence matrix estimation10.1109/TVCG.2024.3372111 ↗
32. Stadler, D., and Beyerer, J. (2022, January 3–8). Modelling ambiguous assignments for multi-person tracking in crowds. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACVW54805.2022.00019 ↗
33. BoostTrack: Boosting the similarity measure and detection confidence for improved multiple object tracking10.1007/s00138-024-01531-5 ↗
34. Bochinski, E., Eiselein, V., and Sikora, T. (September, January 29). High-speed tracking-by-detection without using image information. Proceedings of the 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Lecce, Italy.
35. Li, W., Mu, J., and Liu, G. (2019, January 27–28). Multiple object tracking with motion and appearance cues. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, Seoul, Republic of Korea.10.1109/ICCVW.2019.00025 ↗
36. ECO, the Evidence & Conclusion Ontology: Community standard for evidence information10.1093/nar/gky1036 ↗
37. Bae, S.H., and Yoon, K.J. (2014, January 23–28). Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.159 ↗
38. Multi-small target detection and tracking based on improved YOLO and SIFT for drones