Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

An Efficient One-Shot Network and Robust Data Associations in Multi-pedestrian Tracking

  • Conference paper
  • First Online:
Knowledge Science, Engineering and Management (KSEM 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14118))

Abstract

Recently, one-shot trackers, which integrate multi-tasks into a unified network, achieve good performances in multi-object video tracking and successfully handle the core challenge of multi-object tracking, that is, how to realize the trade-off between the high accuracy and real-time performance. In this paper, we abandon the traditional approach of redundant backbones and feature fusion networks commonly used by one-shot trackers, and propose a new one-shot model that is faster and lighter. We propose a new channel-spatial attention module to improve the detection and re-identification performance of the one-shot model for more robust tracking. Furthermore, in order to deal with complex video tracking scenarios more robust, we have made innovations in data association and proposed a new robust association method, which combines the advantages of the motion, appearance and the detection information to associate. On the MOT20 testing set, our proposed one-shot model with robust associations termed as BFMOT reduces the number of ID switches by 52.1% and improves the tracking accuracy (i.e. MOTA) by 6.7% compared with the state-of-the-art tracker. BFMOT runs close to 30 FPS on MOT16,17 testing sets, which is more oriented to real-time tracking.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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. Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)

  2. Zhou, X., Koltun, V., Krähenbühl, P.: Tracking objects as points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 474–490. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_28

    Chapter  Google Scholar 

  3. Zhang, Y., et al.: FairMOT: on the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vis. 129(11), 3069–3087 (2021)

    Google Scholar 

  4. Wu, J., et al.: Track to detect and segment: an online multi-object tracker. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12352–12361 (2021)

    Google Scholar 

  5. Wang, Y., Kitani, K., Weng, X.: Joint object detection and multi-object tracking with graph neural networks. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13708–13715 (2021)

    Google Scholar 

  6. Mostafa, R., Baraka, H., Bayoumi, A.: LMOT: efficient light-weight detection and tracking in crowds. IEEE Access 10, 83085–83095 (2022)

    Google Scholar 

  7. Wojke, N., Bewley, A., Paulus, P.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3645–3649 (2017)

    Google Scholar 

  8. Chen, L., et al.: Real-time multiple people tracking with deeply learned candidate selection and person re-identification. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6 (2018)

    Google Scholar 

  9. Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. LNCS, vol. 13682, pp. 1–21. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20047-2_1

  10. Hu, J., Li S., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)

    Google Scholar 

  11. Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1

    Chapter  Google Scholar 

  12. Kalman, R.E.: A new approach to linear filtering and prediction problems, pp. 35–45 (1960)

    Google Scholar 

  13. Lu, Z., et al.: RetinaTrack: online single stage joint detection and tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668–14678 (2020)

    Google Scholar 

  14. Wang, Z., Zheng, L., Liu, Y., Li, Y., Wang, S.: Towards real-time multi-object tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 107–122. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_7

    Chapter  Google Scholar 

  15. Liang, C., et al.: Rethinking the competition between detection and Re-ID in Multi-Object Tracking. arXiv preprint arXiv:2010.12138v2 (2020)

  16. Liang, C., et al.: One more check: making “fake background” be tracked again. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 2, pp. 1546–1554 (2022)

    Google Scholar 

  17. Wang, Q., et al.: Multiple object tracking with correlation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3876–3886 (2021)

    Google Scholar 

  18. Bewley, A., et al.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464–3468 (2016)

    Google Scholar 

  19. Wang, C., Alexey, B., Liao, H.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Preprint arXiv:2207.02696 (2022)

  20. Lin, T., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

    Google Scholar 

  21. Tan, M., Pang, R., Le, Q.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781–10790 (2020)

    Google Scholar 

  22. Milan, A., Leal-Taixé, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)

  23. Dendorfer, P., et al.: MOTChallenge: a benchmark for single-camera multiple target tracking. Int. J. Comput. Vis. 129(4), 845–881 (2021)

    Google Scholar 

  24. Lin, T., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  25. Kuhn, H.: The Hungarian method for the assignment problem. Naval Res. Logistics Q. 2.1-2, 83–97 (1955)

    Google Scholar 

  26. Zhang, S., Benenson, R., Schiele, B.: CityPersons: a diverse dataset for pedestrian detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3213–3221 (2017)

    Google Scholar 

  27. Ess, A., et al.: A mobile vision system for robust multi-person tracking. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)

    Google Scholar 

  28. Aharon, N., Orfaig R., Bobrovsky B.: BoT-SORT: robust associations multi-pedestrian tracking. arXiv preprint arXiv:2206.14651v2 (2022)

  29. Dollár, P., et al.: Pedestrian detection: a benchmark. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 304–311 (2009)

    Google Scholar 

  30. Xiao, T., et al.: Joint detection and identification feature learning for person search. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3415–3424 (2017)

    Google Scholar 

  31. Zheng, L., et al.: Person re-identification in the wild. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1367–1376 (2017)

    Google Scholar 

  32. Shao, S., et al.: CrowdHuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)

  33. Dendorfer, P., et al.: MOT20: a benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003 (2020)

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

    Google Scholar 

  35. Luiten, J., et al.: HOTA: a higher order metric for evaluating multi-object tracking. Int. J. Comput. Vis. 129(2), 548–578 (2021)

    Google Scholar 

  36. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  37. Glenn, J.: https://github.com/ultralytics/yolov5/releases/tag/v6.1

  38. Cai, J., et al.: MeMOT: multi-object tracking with memory. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8090–8100 (2022)

    Google Scholar 

  39. Meinhardt, T., et al.: TrackFormer: multi-object tracking with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844–8854 (2022)

    Google Scholar 

  40. Zhou, X., et al.: Global tracking transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8771–8780 (2022)

    Google Scholar 

  41. Hyun, J., et al.: Detection recovery in online multi-object tracking with Sparse Graph Tracker. arXiv preprint arXiv:2205.00968 (2022)

  42. Zhu, T., et al.: Looking beyond two frames: end-to-end multi-object tracking using spatial and temporal transformers. IEEE Trans. Pattern Anal. Mach. Intell. (2022)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Computer and Information Science, Southwest University, Chongqin, China

    Fuxiao He & Guoqiang Xiao

Authors
  1. Fuxiao He
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guoqiang Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Guoqiang Xiao .

Editor information

Editors and Affiliations

  1. Peking University, Beijing, China

    Zhi Jin

  2. South China Normal University, Guangzhou, China

    Yuncheng Jiang

  3. Babeș-Bolyai University, Cluj-Napoca, Romania

    Robert Andrei Buchmann

  4. Ulster University, Belfast, UK

    Yaxin Bi

  5. Babeș-Bolyai University, Cluj-Napoca, Romania

    Ana-Maria Ghiran

  6. South China Normal University, Guangzhou, China

    Wenjun Ma

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

He, F., Xiao, G. (2023). An Efficient One-Shot Network and Robust Data Associations in Multi-pedestrian Tracking. In: Jin, Z., Jiang, Y., Buchmann, R.A., Bi, Y., Ghiran, AM., Ma, W. (eds) Knowledge Science, Engineering and Management. KSEM 2023. Lecture Notes in Computer Science(), vol 14118. Springer, Cham. https://doi.org/10.1007/978-3-031-40286-9_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-40286-9_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-40285-2

  • Online ISBN: 978-3-031-40286-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation