Skip to main content
SpringerLink
Log in

Reinforce Model Tracklet for Multi-Object Tracking

  • Conference paper
  • First Online:
Advances in Computer Graphics (CGI 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14497))

Included in the following conference series:

  • 174 Accesses

Abstract

Recently, most multi-object tracking algorithms adopt the idea of tracking-by-detection. Related studies have shown that significant improvements with the development of detectors. However, missed detection and false detection are more serious in occlusion situations. Therefore, the tracker uses tracklet (short trajectories) to generate more perfect trajectories. There are many tracklet generation algorithms, but the fragmentation problem is still prevalent in crowded scenes. Fixed window tracklet generation strategies are not suitable for dynamic environments with occlusions. To solve this problem, we propose a reinforcement learning-based framework for tracklet generation, where we regard tracklet generation as a Markov decision process and then utilize reinforcement learning to dynamically predict the window size for generating tracklet. Additionally, we introduce a novel scheme that incorporates the temporal order of tracklet for association. Experiments of our method on the MOT17 dataset demonstrate its effectiveness, achieving competitive results compared to the most advanced methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Luo, W., et al.: Multiple object tracking: a literature review (2014). arXiv:1409.7618. http://arxiv.org/abs/1409.7618

  2. Wang, S., Sheng, H., Yang, D., Zhang, Y., Wu, Y., Wang, S.: Extendable multiple nodes recurrent tracking framework with RTU++. IEEE Trans. Image Process. 31, 5257–5271 (2022)

    Article  Google Scholar 

  3. Sheng, H., et al.: High confident evaluation for smart city services. Front. Environ. Sci. 10, 950055 (2022)

    Article  Google Scholar 

  4. Wu, Y., Sheng, H., Zhang, Y., Wang, S., Xiong, Z., Ke, W.: Hybrid motion model for multiple object tracking in mobile devices. IEEE Internet Things J. 10, 1–14 (2022)

    Google Scholar 

  5. Wang, S., Sheng, H., Zhang, Y., Yang, D., Shen, J., Chen, R.: Blockchain-empowered distributed multi-camera multi-target tracking in edge computing. IEEE Trans. Ind. Inform. 1–14 (2023)

    Google Scholar 

  6. Girbau, A., Marques, F., Satoh, S.: Multiple object tracking from appearance by hierarchically clustering tracklets. In: 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, 21–24 November 2022 (2022)

    Google Scholar 

  7. Cao, J., Zhang, J., Li, B., Gao, L., Zhang, J.: RetinaMOT: rethinking anchor-free YOLOv5 for online multiple object tracking. Complex Intell. Syst. (2023)

    Google Scholar 

  8. Sun, P., et al.: TransTrack: Multiple Object Tracking with Transformer, arXiv:2012.15460 (2020)

  9. Xu, Y., Ban, Y., Delorme, G., Gan, C., Rus, D., Alameda-Pineda, X.: TransCenter: Transformers with Dense Queries for Multiple-Object Tracking, arXiv (2021)

    Google Scholar 

  10. Wang, S., Sheng, H., Zhang, Y., Wu, Y., Xiong, Z.: A general recurrent tracking framework without real data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)

    Google Scholar 

  11. Sheng, H., Chen, J., Zhang, Y., Ke, W., Xiong, Z., Yu, J.: Iterative multiple hypothesis tracking with tracklet-level association. IEEE Trans. Circuits Syst. Video Technol. 29(12), 3660–3672 (2019)

    Article  Google Scholar 

  12. Dollar, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. Pattern Anal. Mach. Intell. 36, 1532–1545 (2014)

    Article  Google Scholar 

  13. Supancic III, J., Ramanan, D.: Tracking as online decision-making: learning a policy from streaming videos with reinforcement learning. In: ICCV, pp. 322–331 (2017)

    Google Scholar 

  14. Sheng, H., et al.: Hypothesis testing based tracking with spatio-temporal joint interaction modeling. IEEE Trans. Circuits Syst. Video Technol. 30(9), 2971–2983 (2020)

    Article  Google Scholar 

  15. Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)

    Article  Google Scholar 

  16. Wang, B., Wang, G., Chan, K.L., Wang, L.: Tracklet association by online target-specific metric learning and coherent dynamics estimation. IEEE Trans. Pattern Anal. Mach. Intell. 39(3), 589–602 (2017)

    Article  Google Scholar 

  17. Yun, S., Choi, J., Yoo, Y., Yun, K., Choi, J.Y.: Action-decision networks for visual tracking with deep reinforcement learning. In: CVPR, pp. 2711–2720 (2017)

    Google Scholar 

  18. Wang, G., Wang, Y., Zhang, H., Gu, R., Hwang, J.-N.: Exploit the connectivity: multi-object tracking with TrackletNet (2018). arXiv:1811.07258. http://arxiv.org/abs/1811.07258

  19. Chen, L., Ai, H., Chen, R., Zhuang, Z.: Aggregate tracklet appearance features for multi-object tracking. IEEE Signal Process. Lett. 26(11), 1613–1617 (2019)

    Article  Google Scholar 

  20. Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. Image Video Process. (2008)

    Google Scholar 

  21. Yang, B., et al.: ST3D: A Simple and Efficient Single Shot Multi-Object Tracker with Multi-Feature Fusion, arXiv preprint arXiv:2002.01604 (2020)

  22. Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. IEEE Trans. Pattern Anal. Mach. Intell. (2017)

    Google Scholar 

  23. Xiang, Y., Alahi, A., Savarese, S.: Learning to track: online multi-object tracking by decision making. In: ICCV, pp. 4705–4713 (2015)

    Google Scholar 

  24. Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: FairMOT: on the fairness of detection and re-identification in multiple object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)

    Google Scholar 

  25. Gu, S., Lillicrap, T., Sutskever, I., Levine, S.: Continuous deep Q-learning with model-based acceleration. In: ICML, pp. 2829–2838 (2016)

    Google Scholar 

  26. Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: ICML, pp. 387–395 (2014)

    Google Scholar 

  27. Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)

    Article  Google Scholar 

  28. Cao, Q., Lin, L., Shi, Y., Liang, X., Li, G.: Attention-aware face hallucination via deep reinforcement learning. In: CVPR, pp. 690–698 (2017)

    Google Scholar 

  29. Liu, S., Zhu, Z., Ye, N., Guadarrama, S., Murphy, K.: Optimization of image description metrics using policy gradient methods. arXiv preprint arXiv:1612.00370 (2016)

  30. MOTChallenge: MOT17: a benchmark for multi-object tracking. http://motchallenge.net/data/MOT17/. Accessed 25 April 2023

  31. Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J. Image Video Process. 2008(1), 1–10 (2008)

    Article  Google Scholar 

  32. Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_2

    Chapter  Google Scholar 

  33. Sheng, H., et al.: Near-online tracking with co-occurrence constraints in blockchain-based edge computing. IEEE Internet Things J. 8(4), 2193–2207 (2021)

    Article  Google Scholar 

  34. Luo, Q., Shao, J., Dang, W., et al.: An efficient multi-scale channel attention network for person re-identification. Vis. Comput. (2023)

    Google Scholar 

  35. Li, Y., et al.: A lightweight scheme of deep appearance extraction for robust online multi-object tracking. Vis. Comput. 1–17 (2023)

    Google Scholar 

  36. Zhang, X., Wang, X., Chunhua, G.: Online multi-object tracking with pedestrian re-identification and occlusion processing. Vis. Comput. 37, 1089–1099 (2021)

    Article  Google Scholar 

  37. Zhang, Y., Yang, Z., Ma, B., et al.: Structural-appearance information fusion for visual tracking. Vis Comput (2023). https://doi.org/10.1007/s00371-023-03013-7

    Article  Google Scholar 

Download references

Acknowledgement

This study is partially supported by the National Key R &D Program of China (No. 2022YFB3306500), the National Natural Science Foundation of China (No. 61872025). Thank you for the support from HAWKEYE Group.

Author information

Authors and Affiliations

  1. State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, 100191, People’s Republic of China

    Jianhong Ouyang, Shuai Wang, Yubin Wu, Jiahao Shen & Hao Sheng

  2. Zhongfa Aviation Institute, Beihang University, Hangzhou, 311115, China

    Jianhong Ouyang, Shuai Wang, Yubin Wu, Jiahao Shen & Hao Sheng

  3. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, 100029, People’s Republic of China

    Yang Zhang

Authors
  1. Jianhong Ouyang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shuai Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yubin Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jiahao Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hao Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianhong Ouyang .

Editor information

Editors and Affiliations

  1. Shanghai Jiao Tong University, Shanghai, China

    Bin Sheng

  2. Shanghai Jiao Tong University, Shanghai, China

    Lei Bi

  3. University of Sydney, Sydney, NSW, Australia

    Jinman Kim

  4. MIRALab-CUI, University of Geneva, Carouge, Geneve, Switzerland

    Nadia Magnenat-Thalmann

  5. Swiss Federal Institute of Technology, Lausanne, Switzerland

    Daniel Thalmann

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ouyang, J., Wang, S., Zhang, Y., Wu, Y., Shen, J., Sheng, H. (2024). Reinforce Model Tracklet for Multi-Object Tracking. In: Sheng, B., Bi, L., Kim, J., Magnenat-Thalmann, N., Thalmann, D. (eds) Advances in Computer Graphics. CGI 2023. Lecture Notes in Computer Science, vol 14497. Springer, Cham. https://doi.org/10.1007/978-3-031-50075-6_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-50075-6_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-50074-9

  • Online ISBN: 978-3-031-50075-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation