Advertisement

Online Multi-target Tracking with Strong and Weak Detections

  • Ricardo Sanchez-Matilla
  • Fabio Poiesi
  • Andrea Cavallaro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9914)

Abstract

We propose an online multi-target tracker that exploits both high- and low-confidence target detections in a Probability Hypothesis Density Particle Filter framework. High-confidence (strong) detections are used for label propagation and target initialization. Low-confidence (weak) detections only support the propagation of labels, i.e. tracking existing targets. Moreover, we perform data association just after the prediction stage thus avoiding the need for computationally expensive labeling procedures such as clustering. Finally, we perform sampling by considering the perspective distortion in the target observations. The tracker runs on average at 12 frames per second. Results show that our method outperforms alternative online trackers on the Multiple Object Tracking 2016 and 2015 benchmark datasets in terms tracking accuracy, false negatives and speed.

Keywords

Multi-Target Tracking Probability Hypothesis Density Particle Filter 

Notes

Acknowledgements

This work was supported in part by the ARTEMIS JU and the UK Technology Strategy Board (Innovate UK) through the COPCAMS Project, under Grant 332913.

References

  1. 1.
    Solera, F., Calderara, S., Cucchiara, R.: Learning to divide and conquer for online multi-target tracking. In: Proceedings of International Conference on Computer Vision, Santiago, CL, December 2015Google Scholar
  2. 2.
    Wang, B., Wang, G., Chan, K., Wang, L.: Tracklet association with online target-specific metric learning. In: Proceedings of Computer Vision and Pattern Recognition, Columbus, OH, USA, June 2014Google Scholar
  3. 3.
    Poiesi, F., Cavallaro, A.: Tracking multiple high-density homogeneous targets. IEEE Trans. on Circ. Syst. Video Technol. 25(4), 623–637 (2015)Google Scholar
  4. 4.
    Possegger, H., Mauthner, T., Roth, P., Bischof, H.: Occlusion geodesics for online multi-object tracking. In: Proceedings of Computer Vision and Pattern Recognition, Columbus, OH, USA, June 2014Google Scholar
  5. 5.
    Shu, G., Dehghan, A., Oreifej, O., Hand, E., Shah, M.: Part-based multiple-person tracking with partial occlusion handling. In: Proceedings of Computer Vision and Pattern Recognition, Rhode Island, USA, June 2012Google Scholar
  6. 6.
    Mahler, R.: A theoretical foundation for the Stein-Winter Probability Hypothesis Density (PHD) multitarget tracking approach. In: Proceedings of MSS National Symposium on Sensor and Data Fusion, San Diego, CA, USA, June 2002Google Scholar
  7. 7.
    Maggio, E., Taj, M., Cavallaro, A.: Efficient multitarget visual tracking using random finite sets. IEEE Trans. Circ. Syst. Video Technol. 18(8), 1016–1027 (2008)CrossRefGoogle Scholar
  8. 8.
    Vo, B.N., Singh, S., Doucet, A.: Sequential Monte Carlo implementation of the PHD filter for multi-target tracking. In: Proceedings of Information Fusion, vol. 2, Queensland, AU, July 2003Google Scholar
  9. 9.
    Mahler, R.: PHD filters of higher order in target number. IEEE Aerosp. Electron. Syst. Mag. 43(4), 1523–1543 (2007)CrossRefGoogle Scholar
  10. 10.
    Panta, K., Vo, B., Singh, S.: Improved probability hypothesis density (PHD) filter for multitarget tracking. In: 2005 3rd International Conference on Intelligent Sensing and Information Processing, December 2005Google Scholar
  11. 11.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of Computer Vision and Pattern Recognition, San Diego, CA, USA, June 2005Google Scholar
  12. 12.
    Felzenszwalb, P.F., Girshick, R., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  13. 13.
    Smedt, F.D., Goedeme, T.: Open framework for combinated pedestrian detection. In: Proceedings of Computer Vision, Imaging and Computer Graphics Theory and Applications, Berlin, GE, March 2015Google Scholar
  14. 14.
    Lin, L., Bar-Shalom, Y., Kirubarajan, T.: Data association combined with the Probability Hypothesis Density Filter for multitarget tracking. In: Proceedings of SPIE, August 2004Google Scholar
  15. 15.
    Panta, K., Vo, B.N., Singh, S., Doucet, A.: Probability Hypothesis Density filter versus multiple hypothesis tracking. In: Proceedings of SPIE, August 2004Google Scholar
  16. 16.
    Kuhn, H., Yaw, B.: The Hungarian method for the assignment problem. Naval Res. Logistics Q. 2, 83–97 (1955)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Poiesi, F., Mazzon, R., Cavallaro, A.: Multi-target tracking on confidence maps: an application to people tracking. Comput. Vis. Image Underst. 117(10), 1257–1272 (2013)CrossRefGoogle Scholar
  18. 18.
    Maggio, E., Cavallaro, A.: Learning scene context for multiple object tracking. IEEE Trans. Image Process. 18(8), 1873–1884 (2009)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Vo, B.N., Singh, S., Doucet, A.: Sequential Monte Carlo methods for multitarget filtering with random finite sets. IEEE Aerosp. Electron. Syst. Mag. 41(4), 1224–1245 (2005)CrossRefGoogle Scholar
  20. 20.
    Arulampalam, M., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. Sig. Process. 50(2), 174–188 (2002)CrossRefGoogle Scholar
  21. 21.
    Leal-Taixé, L., Milan, A., Reid, I., Roth, S., Schindler, K.: MOTChallenge 2015: towards a benchmark for multi-target tracking, April 2015. arXiv:1504.01942 [cs]
  22. 22.
    Milan, A., Leal-Taixé, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking, March 2016. arXiv:1603.00831 [cs]
  23. 23.
    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: Proceedings of Computer Vision and Pattern Recognition, Las Vegas, NV, USA, June 2016Google Scholar
  24. 24.
    Dollar, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532–1545 (2014)CrossRefGoogle Scholar
  25. 25.
    Kasturi, R., Goldgof, D., Soundararajan, P., Manohar, V., Garofolo, J., Bowers, R., Boonstra, M., Korzhova, V., Zhang, J.: Framework for performance evaluation of face, text, and vehicle detection and tracking in video: data, metrics, and protocol. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 319–336 (2009)CrossRefGoogle Scholar
  26. 26.
    Li, Y., Huang, C., Nevatia, R.: Learning to associate: HybridBoosted multi-target tracker for crowded scene. In: Proceedings of Computer Vision and Pattern Recognition, Miami, FL, USA, June 2009Google Scholar
  27. 27.
    Xiang, Y., Alahi, A., Savarese, S.: Learning to track: online multi-object tracking by decision making. In: Proceedings of International Conference on Computer Vision, Santiago, CL, December 2015Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Ricardo Sanchez-Matilla
    • 1
  • Fabio Poiesi
    • 1
  • Andrea Cavallaro
    • 1
  1. 1.Centre for Intelligent SensingQueen Mary University of LondonLondonUK

Personalised recommendations