Abstract
Although there is significant progress and wide applications in multi object tracking technology in recent years, the occlusion problem has always been an obstacle, especially in subway systems with dense crowds, high mobility, and narrow spaces. This difficulty greatly affects the accuracy of tracking and identification. Aiming at the problem of crowd occlusion in subway stations, based on the FairMOT [1], we improve the model and apply it to the subway so that it can count the number of people moving in different directions and enrich the data of pedestrian flow. However, FairMOT still cannot solve the occlusion problem in subway scenes because it cannot handle missing pedestrians effectively. Therefore, we propose three methods to solve the occlusion problem, including a new convolution branch, feature matching and handling of missing. Then, we show how to count the number of people moving in different directions. Experimental results demonstrate that our innovation can effectively improve the tracking performance not only in the case of short-distance double cross occlusion but also for long-distance dense crowd occlusion and building occlusion.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: FairMOT: on the fairness of detection and re-identification in multiple object tracking, eprint arXiv:2004.01888 (2020)
Chen, L., Ai, H., Zhuang, Z., Shang, C.: Real-time multiple people tracking with deeply learned candidate selection and person re-identification. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), San Diego, CA, USA, pp. 1–6 (2018). https://doi.org/10.1109/ICME.2018.8486597
Leal-Taixé, L., Milan, A., Reid, I., Roth, S., Schindler, K.: Motchallenge 2015: towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942 (2015)
Song, Y., Yoon, K., Yoon, Y., Yow, K.C., Jeon, M.: Online multi-object tracking with GMPHD filter and occlusion group management. IEEE Access 7, 165103–165121 (2019). https://doi.org/10.1109/ACCESS.2019.2953276
Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, pp. 3645–3649 (2017). https://doi.org/10.1109/ICIP.2017.8296962
Wang, L., Xu, L., Kim, M.Y., Rigazico, L., Yang, M.: Online multiple object tracking via flow and convolutional features. In: 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, pp. 3630–3634 (2017). https://doi.org/10.1109/ICIP.2017.8296959
Saleh, F., Aliakbarian, S., Rezatofighi, H., Salzmann, M., Gould, S.: Probabilistic tracklet scoring and inpainting for multiple object tracking, eprint arXiv:2012.02337 (2020)
Abbaspour, M., Masnadi-Shirazi, M.A.: Online multi-object tracking with delta-GLMB filter based on occlusion and identity switch handling, eprint arXiv:2011.10111 (2020)
Yoon, Y., Boragule, A., Song, Y., Yoon, K., Jeon, M.: Online multi-object tracking with historical appearance matching and scene adaptive detection filtering. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Auckland, New Zealand, 2018, pp. 1–6 (2018). https://doi.org/10.1109/AVSS.2018.8639078
Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 941–951 (2019)
Peng, J., Gu, Y., Wang, Y., Wang, C., Li, J., Huang, F.: Dense scene multiple object tracking with box-plane matching, eprint arXiv:2007.15576 (2020)
Unde, A.S., Rameshan, R.M.: MOTS R-CNN: cosine-margin-triplet loss for multi-object tracking, eprint arXiv:2102.03512 (2021)
Ren, L., Lu, J., Wang, Z., Tian, Q., Zhou, J.: Collaborative deep reinforcement learning for multi-object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 605–621. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_36
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Acknowledgment
This work was supported in part by the Shenzhen Science and Technology Program under Grant JCYJ2018030512 3922293, JCYJ20190808143415801. The authors would also like to thank the anonymous reviewers.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, G., Yang, Y., Zhong, X., Yang, Y. (2022). An Improved FairMOT Method for Crowd Tracking and Counting in Subway Passages. In: Zhang, Z. (eds) 2021 6th International Conference on Intelligent Transportation Engineering (ICITE 2021). ICITE 2021. Lecture Notes in Electrical Engineering, vol 901. Springer, Singapore. https://doi.org/10.1007/978-981-19-2259-6_11
Download citation
DOI: https://doi.org/10.1007/978-981-19-2259-6_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2258-9
Online ISBN: 978-981-19-2259-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)