Skip to main content
SpringerLink
Log in

Pedestrian Multi-object Tracking Based on ResNeXt and FairMOT

  • Conference paper
  • First Online:
Advances in Automation, Mechanical and Design Engineering (SAMDE 2022)

Part of the book series: Mechanisms and Machine Science ((Mechan. Machine Science,volume 138))

  • 139 Accesses

Abstract

Multi-object tracking is an important branch in the field of computer vision. To address the shortcomings of the current paradigm of following detection-based multi-object tracking, this paper proposes an improved algorithm based on FairMOT. Firstly, ResNeXt50 is used as the backbone network, which makes the model more capable of feature extraction, secondly, a normalization-based attention module (NAM) is added to Resblock to suppress less significant weights and focus more on the desired target regions to extract more effective features. The MOTA metric and IDF1 metric achieve 68.8% and 68.1% respectively on the MOT17 dataset. The experimental results demonstrate the performance of the proposed algorithm with some advantages.

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 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover 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., Xing, J., Milan, A., et al.: Multiple object tracking: a literature review. Artif. Intell. 293, 103448 (2021)

    Article  MathSciNet  Google Scholar 

  2. Yang, C., Xu, T., Lv, M., et al.: Pedestrian angle recognition based on JDE multi-object tracking algorithm. In: Proceedings of the 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), pp. 647–651. IEEE (2022)

    Google Scholar 

  3. Zhang, Y., Wang, C., Wang, X., et al.: Fairmot: On the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vision 129(11), 3069–3087 (2021)

    Article  MathSciNet  Google Scholar 

  4. Bewley, A., Ge, Z., Ott, L., et al.: Simple online and realtime tracking. In: Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464–3468. IEEE (2016)

    Google Scholar 

  5. Kalman, R.: A new approach to linear filtering and prediction problems. J. Basic Eng., 35–45 (1960)

    Google Scholar 

  6. Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. (NRL) 52(1), 7–21 (2005)

    Article  Google Scholar 

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

    Google Scholar 

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

    Google Scholar 

  9. Wang, Z., Zheng, L., Liu, Y., et al.: Towards real-time multi-object tracking. In: Proceedings of the European Conference on Computer Vision, pp. 107–122. Springer, Cham (2020)

    Google Scholar 

  10. Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)

  11. Duan, K., Bai, S., Xie, L. et al.: Centernet: keypoint triplets for object detection. In: Proceedings of Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6569–6578 (2019)

    Google Scholar 

  12. He, K., Zhang, X., Ren, S. et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  13. Yu, F., Wang, D., Shelhamer, E. et al.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2403–2412 (2018)

    Google Scholar 

  14. Xie, S., Girshick, R., Dollár, P. et al.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)

    Google Scholar 

  15. Deng, J., Dong, W., Socher, R. et al.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)

    Google Scholar 

  16. Guo, M.H., Xu, T.X., Liu, J.J. et al.: Attention mechanisms in computer vision: a survey. Comput. Vis. Media, 1–38 (2022)

    Google Scholar 

  17. Liu, Y., Shao, Z., Teng, Y. et al.: NAM: Normalization-based Attention Module. arXiv preprint arXiv:2111.12419 (2021)

  18. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132–7141 (2018)

    Google Scholar 

  19. Park, J., Woo, S., Lee, J.Y. et al.: Bam: bottleneck attention module. arXiv preprint arXiv:1807.06514 (2018)

  20. Woo, S., Park, J., Lee, J.Y. et al.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)

    Google Scholar 

  21. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)

    Google Scholar 

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

    Google Scholar 

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

    Google Scholar 

  24. Leal-Taixé, L., Milan, A., Reid, I. et al.: Motchallenge 2015: towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942 (2015)

  25. Milan, A., Leal-Taixé, L., Reid, I. et al.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)

  26. Dendorfer, P., Rezatofighi, H., Milan, A. et al.: Mot20: a benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003 (2020)

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

    Article  Google Scholar 

  28. Liu, Z., Wang, S., Yao, L. et al.: Online multi-object tracking under moving unmanned aerial vehicle platform based on object detection and feature extraction network. J. Shanghai Jiaotong Univ. (Science), 1–12 (2022)

    Google Scholar 

  29. Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: Proceedings of the Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 941–951 (2019)

    Google Scholar 

  30. Pang, B., Li, Y., Zhang, Y. et al.: Tubetk: adopting tubes to track multi-object in a one-step training model. In: Proceedings of the Proceedings of Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6308–6318 (2020)

    Google Scholar 

  31. Peng, J., Wang, C., Wan, F. et al.: Chained-tracker: chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking. In: Proceedings of the European Conference on Computer Vision, pp. 145–161. Springer, Cham (2020)

    Google Scholar 

  32. Zhou, X., Koltun, V., Krähenbühl, P.: Tracking objects as points. In: Proceedings of the European Conference on Computer Vision, pp. 474–490. Springer, Cham (2020)

    Google Scholar 

Download references

Acknowledgements

Our thanks to National Natural Science Foundation of China (No. 61861037) and Ningxia University Graduate Innovation Research Project (No. CXXM202223).

Author information

Authors and Affiliations

  1. School of Physics and Electronic-Electrical Engineering, Ningxia Key Laboratory of Intelligent Sensing for Desert Information, Ningxia University, Yinchuan, China

    Yuting He, Jin Che & Jinman Wu

Authors
  1. Yuting He
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jin Che
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jinman Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuting He .

Editor information

Editors and Affiliations

  1. DIMEG, University of Calabria, Rende, Italy

    Giuseppe Carbone

  2. SP2MI—Site du Futuroscope, University of Poitiers, Poitiers, France

    Med Amine Laribi

  3. School of Artificial Intelligence OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, Shaanxi, China

    Zhiyu Jiang

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, Y., Che, J., Wu, J. (2023). Pedestrian Multi-object Tracking Based on ResNeXt and FairMOT. In: Carbone, G., Laribi, M.A., Jiang, Z. (eds) Advances in Automation, Mechanical and Design Engineering. SAMDE 2022. Mechanisms and Machine Science, vol 138. Springer, Cham. https://doi.org/10.1007/978-3-031-40070-4_15

Download citation

Publish with us

Policies and ethics

Search

Navigation