Abstract
Within the tracking-by-detection framework, multi-object tracking (MOT) has always been plagued by missing detection. To address this problem, existing methods usually predict new positions of the trajectories first to provide more candidate bounding boxes (BBoxes), and then use non-maximum suppression (NMS) to eliminate the redundant BBoxes. However, when two BBoxes belonging to different objects have a significant intersection over union (IoU) due to occlusion, NMS will mistakenly filter out the one with lower confidence score, and these methods ignore the missing detection caused by NMS. We propose a joint re-detection and re-identification tracker (JDI) for MOT, consisting of two components, trajectory re-detection and NMS with re-identification (ReID). Specifically, the trajectory re-detection could predict new position of the trajectory in detection, a more reliable way than motion model (MM), based on feature matching. Furthermore, we propose to embed ReID features into NMS and take the similarity of the ReID features as an additional necessary condition to determine whether two BBoxes are the same object. Based on the “overlap degree” calculated by IoU and the similarity of ReID features, accurate filtering can be achieved through double-checking. We demonstrate the effectiveness of our tracking components with ablative experiments and surpass the state-of-the-art methods on the three tracking benchmarks MOT16, MOT17, and MOT20.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andriyenko, A., Schindler, K., Roth, S.: Discrete-continuous optimization for multi-target tracking. In: CVPR, pp. 1926–1933 (2012)
Bergmann, P., Meinhardt, T., Leal-Taixé, L.: Tracking without bells and whistles. In: ICCV, pp. 941–951 (2019)
Bewley, A., Ge, Z., Ott, L., Ramos, F.T., Upcroft, B.: Simple online and realtime tracking. In: ICIP, pp. 3464–3468 (2016)
Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS - improving object detection with one line of code. In: ICCV, pp. 5562–5570 (2017)
Brasó, G., Leal-Taixé, L.: Learning a neural solver for multiple object tracking. In: CVPR, pp. 6246–6256 (2020)
Chen, L., Ai, H., Zhuang, Z., Shang, C.: Real-time multiple people tracking with deeply learned candidate selection and person re-identification. In: ICME, pp. 1–6 (2018)
Chu, P., Ling, H.: FAMNet: joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking. In: ICCV, pp. 6171–6180 (2019)
Dai, P., Weng, R., Choi, W., Zhang, C., He, Z., Ding, W.: Learning a proposal classifier for multiple object tracking. In: CVPR, pp. 2443–2452 (2021)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)
Guo, D., Wang, J., Cui, Y., Wang, Z., Chen, S.: SiamCAR: siamese fully convolutional classification and regression for visual tracking. In: CVPR, pp. 6268–6276 (2020)
Guo, S., Wang, J., Wang, X., Tao, D.: Online multiple object tracking with cross-task synergy. In: CVPR, pp. 8136–8145 (2021)
Hornáková, A., Henschel, R., Rosenhahn, B., Swoboda, P.: Lifted disjoint paths with application in multiple object tracking. In: ICML, pp. 4364–4375 (2020)
Huang, X., Ge, Z., Jie, Z., Yoshie, O.: NMS by representative region: towards crowded pedestrian detection by proposal pairing. In: CVPR, pp. 10747–10756 (2020)
Karthik, S., Prabhu, A., Gandhi, V.: Simple unsupervised multi-object tracking. arXiv 2006.02609 (2020). https://arxiv.org/abs/2006.02609
Liu, Q., Chu, Q., Liu, B., Yu, N.: GSM: graph similarity model for multi-object tracking. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI), pp. 530–536 (2020)
Liu, S., Huang, D., Wang, Y.: Adaptive NMS: refining pedestrian detection in a crowd. In: CVPR, pp. 6459–6468 (2019)
Nie, W., Liu, A., Su, Y., Gao, Z.: An effective tracking system for multiple object tracking in occlusion scenes. In: MMM, pp. 206–216 (2013)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Ren, W., Wang, X., Tian, J., Tang, Y., Chan, A.B.: Tracking-by-counting: using network flows on crowd density maps for tracking multiple targets. IEEE Trans. Image Process. 30, 1439–1452 (2021)
Stadler, D., Beyerer, J.: Improving multiple pedestrian tracking by track management and occlusion handling. In: CVPR, pp. 10958–10967 (2021)
Tang, S., Andriluka, M., Andres, B., Schiele, B.: Multiple people tracking by lifted multicut and person re-identification. In: CVPR, pp. 3701–3710 (2017)
Wang, F., Luo, L., Zhu, E.: Two-stage real-time multi-object tracking with candidate selection. In: MMM, pp. 49–61 (2021)
Wang, G., Wang, Y., Gu, R., Hu, W., Hwang, J.: Split and connect: a universal tracklet booster for multi-object tracking. arXiv 2105.02426 (2021). https://arxiv.org/abs/2105.02426
Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: ICIP, pp. 3645–3649 (2017)
Xu, Y., Osep, A., Ban, Y., Horaud, R., Leal-Taixé, L., Alameda-Pineda, X.: How to train your deep multi-object tracker. In: CVPR, pp. 6786–6795 (2020)
Yang, F., Choi, W., Lin, Y.: Exploit all the layers: Fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers. In: CVPR, pp. 2129–2137 (2016)
Yin, J., Wang, W., Meng, Q., Yang, R., Shen, J.: A unified object motion and affinity model for online multi-object tracking. In: CVPR, pp. 6767–6776 (2020)
Zhong, X., Tan, M., Ruan, W., Huang, W., Xie, L., Yuan, J.: Dual-direction perception and collaboration network for near-online multi-object tracking. In: ICIP, pp. 2111–2115 (2020)
Zhou, X., Koltun, V., Krähenbühl, P.: Tracking objects as points. In: ECCV, pp. 474–490 (2020)
Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., Yang, M.: Online multi-object tracking with dual matching attention networks. In: ECCV, pp. 379–396 (2018)
Acknowledgement
This work was supported in part by the Department of Science and Technology, Hubei Provincial People’s Government under Grant 2021CFB513, in part by the Hubei Key Laboratory of Transportation Internet of Things under Grant 2020III026GX, and in part by the Fundamental Research Funds for the Central Universities under Grant 191010001.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
He, J., Zhong, X., Yuan, J., Tan, M., Zhao, S., Zhong, L. (2022). Joint Re-Detection and Re-Identification for Multi-Object Tracking. In: Þór Jónsson, B., et al. MultiMedia Modeling. MMM 2022. Lecture Notes in Computer Science, vol 13141. Springer, Cham. https://doi.org/10.1007/978-3-030-98358-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-98358-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98357-4
Online ISBN: 978-3-030-98358-1
eBook Packages: Computer ScienceComputer Science (R0)