Advertisement

Consistent Online Multi-object Tracking with Part-Based Deep Network

  • Chuanzhi Xu
  • Yue ZhouEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11257)

Abstract

Multi-object tracking is still a challenge problem in complex and crowded scenarios. Mismatches will always happen when objects have similar appearance or are occluded with each other. In this paper, we appeal for more attention to the consistency of the trajectories and propose a part-based deep network which employs ROI pooling method to extract full and part-based features for the objects. An occlusion detector is proposed to predict the occlusion degree and guide the procedure of part-based feature fusion and appearance model update. In this way, the feature extraction speed of our tracker is faster, and the objects can be associated correctly even if they are partly occluded. Besides, we train the network based on siamese architecture to learn a dissimilarity metric between pairs of identities. Extensive experiments with multiple evaluation metrics show that our tracker can associate the objects consistently and gain a significant improvement in tracking accuracy.

Keywords

Multi-object tracking Part-based model Occlusion detector Consistent trajectories 

References

  1. 1.
    Bae, S.H., Yoon, K.J.: Confidence-based data association and discriminative deep appearance learning for robust online multi-object tracking. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2017)Google Scholar
  2. 2.
    Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. Eurasip J. Image Video Process. 2008(1), 246309 (2008)Google Scholar
  3. 3.
    Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: IEEE International Conference on Image Processing, pp. 3464–3468 (2016)Google Scholar
  4. 4.
    Bochinski, E., Eiselein, V., Sikora, T.: High-speed tracking-by-detection without using image information. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (2017)Google Scholar
  5. 5.
    Chari, V., Lacoste-Julien, S., Laptev, I., Sivic, J.: On pairwise cost for multi-object network flow tracking. CoRR, abs/1408.3304 (2014)Google Scholar
  6. 6.
    Chen, X., Qin, Z., An, L., Bhanu, B.: Multiperson tracking by online learned grouping model with nonlinear motion context. IEEE Trans. Circuits Syst. Video Technol. 26(12), 2226–2239 (2016)CrossRefGoogle Scholar
  7. 7.
    Chopra, S., Hadsell, R., Lecun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 539–546 (2005)Google Scholar
  8. 8.
    Eiselein, V., Arp, D., Ptzold, M., Sikora, T.: Real-time multi-human tracking using a probability hypothesis density filter and multiple detectors. In: IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, pp. 325–330 (2012)Google Scholar
  9. 9.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)Google Scholar
  10. 10.
    Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)Google Scholar
  11. 11.
    Henschel, R., Lealtaix, L., Cremers, D., Rosenhahn, B.: A novel multi-detector fusion framework for multi-object tracking. Eprint arXiv:1705.08314 (2017)
  12. 12.
    Huang, C., Wu, B., Nevatia, R.: Robust object tracking by hierarchical association of detection responses. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 788–801. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-88688-4_58CrossRefGoogle Scholar
  13. 13.
    Kieritz, H., Becker, S., Hubner, W., Arens, M.: Online multi-person tracking using integral channel features. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 122–130 (2016)Google Scholar
  14. 14.
    Kim, C., Li, F., Ciptadi, A., Rehg, J.M.: Multiple hypothesis tracking revisited. In: IEEE International Conference on Computer Vision, pp. 4696–4704 (2015)Google Scholar
  15. 15.
    Lee, B., Erdenee, E., Jin, S., Nam, M.Y., Jung, Y.G., Rhee, P.K.: Multi-class multi-object tracking using changing point detection. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 68–83. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_6CrossRefGoogle Scholar
  16. 16.
    Milan, A., Leal-Taixe, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. Eprint arXiv:1603.00831 (2016)
  17. 17.
    Milan, A., Roth, S., Schindler, K.: Continuous energy minimization for multitarget tracking. IEEE Trans. Pattern Anal. Mach. Intell. 36(1), 58–72 (2013)CrossRefGoogle Scholar
  18. 18.
    Ren, S., Girshick, R., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137 (2017)CrossRefGoogle Scholar
  19. 19.
    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_2CrossRefGoogle Scholar
  20. 20.
    Sadeghian, A., Alahi, A., Savarese, S.: Tracking the untrackable: learning to track multiple cues with long-term dependencies. Eprint arXiv:1701.01909 (2017)
  21. 21.
    Sanchez-Matilla, R., Poiesi, F., Cavallaro, A.: Online multi-target tracking with strong and weak detections. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 84–99. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_7CrossRefGoogle Scholar
  22. 22.
    Smeulders, A.W., Chu, D.M., Cucchiara, R., Calderara, S., Dehghan, A., Shah, M.: Visual tracking: an experimental survey. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1442–68 (2014)CrossRefGoogle Scholar
  23. 23.
    Tang, S., Andriluka, M., Andres, B., Schiele, B.: Multiple people tracking by lifted multicut and person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3539–3548 (2017)Google Scholar
  24. 24.
    Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: IEEE International Conference on Image Processing, pp. 3645–3649 (2017)Google Scholar
  25. 25.
    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: Computer Vision and Pattern Recognition, pp. 2129–2137 (2016)Google Scholar
  26. 26.
    Yu, F., Li, W., Li, Q., Liu, Y., Shi, X., Yan, J.: POI: multiple object tracking with high performance detection and appearance feature. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 36–42. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_3CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Institute of Image Processing and Pattern RecognitionShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations