International Journal of Computer Vision

, Volume 122, Issue 3, pp 484–501 | Cite as

Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions

Article

Abstract

We describe an end-to-end framework for learning parameters of min-cost flow multi-target tracking problem with quadratic trajectory interactions including suppression of overlapping tracks and contextual cues about co-occurrence of different objects. Our approach utilizes structured prediction with a tracking-specific loss function to learn the complete set of model parameters. In this learning framework, we evaluate two different approaches to finding an optimal set of tracks under a quadratic model objective, one based on an linear program (LP) relaxation and the other based on novel greedy variants of dynamic programming that handle pairwise interactions. We find the greedy algorithms achieve almost equivalent accuracy to the LP relaxation while being up to 10\(\times \) faster than a commercial LP solver. We evaluate trained models on three challenging benchmarks. Surprisingly, we find that with proper parameter learning, our simple data association model without explicit appearance/motion reasoning is able to achieve comparable or better accuracy than many state-of-the-art methods that use far more complex motion features or appearance affinity metric learning.

Keywords

Multi-target tracking Data association Network-flow Structured prediction 

References

  1. Bae, S. H., & Yoon, K. J. (2014). Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. In Proceedings of CVPR.Google Scholar
  2. Bernardin, K., & Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: The clear MOT metrics. Journal on Image Video Processing. doi:10.1155/2008/246309.
  3. Brau, E., Guan, J., Simek, K., Del Pero, L., Reimer Dawson, C., & Barnard, K. (2013). Bayesian 3D tracking from monocular video. In Proceedings of ICCV.Google Scholar
  4. Brendel, W., Amer, M., & Todorovic, S. (2011). Multiobject tracking as maximum weight independent set. In Proceedings of CVPR.Google Scholar
  5. Butt, A. A., & Collins, R. T. (2013). Multi-target tracking by Lagrangian relaxation to min-cost network flow. In Proceedings of CVPR.Google Scholar
  6. Chari, V., Lacoste-Julien, S., Laptev, I., & Sivic, J. (2015). On pairwise costs for network flow multi-object tracking. In Proceedings of CVPR.Google Scholar
  7. Choi, W. (2015). Near-online multi-target tracking with aggregated local flow descriptor. In Proceedings of ICCV.Google Scholar
  8. Choi, W., & Savarese, S. (2012). A unified framework for multi-target tracking and collective activity recognition. In Proceedings of ECCV.Google Scholar
  9. Dehghan, A., Tian, Y., Torr, P. H., & Shah, M. (2015). Target identity-aware network flow for online multiple target tracking. In Proceedings of CVPR.Google Scholar
  10. Desai, C., Ramanan, D., & Fowlkes, C. (2009). Discriminative models for multi-class object layout. In Proceedings of ICCV.Google Scholar
  11. Dollár, P., Appel, R., Belongie, S., & Perona, P. (2014). Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1532–1545.CrossRefGoogle Scholar
  12. Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9), 1627–1645.CrossRefGoogle Scholar
  13. Finley, T., & Joachims, T. (2008). Training structural SVMs when exact inference is intractable. In Proceedings of ICML.Google Scholar
  14. Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? The KITTI vision benchmark suite. In Proceedings of CVPR.Google Scholar
  15. Ahuja, R. K., Magnanti, T. L., & Orlin, J. B. (1993). Network flows: Theory, algorithms, and applications. Upper Saddle River, NJ: Prentice-Hall, Inc.MATHGoogle Scholar
  16. Geiger, A., Lauer, M., Wojek, C., Stiller, C., & Urtasun, R. (2014). 3D traffic scene understanding from movable platforms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(5), 1012–1025.CrossRefGoogle Scholar
  17. Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The KITTI dataset. International Journal of Robotics Research, 32(11), 1231–1237.CrossRefGoogle Scholar
  18. Joachims, T., Finley, T., & Yu, C. N. (2009). Cutting-plane training of structural SVMs. Machine Learning, 77(1), 27–59.CrossRefMATHGoogle Scholar
  19. Joulin, A., Tang, K., & Fei-Fei, L. (2014). Efficient image and video co-localization with Frank–Wolfe algorithm. In Proceedings of ECCV.Google Scholar
  20. Kim, S., Kwak, S., Feyereisl, J., & Han, B. (2013). Online multi-target tracking by large margin structured learning. In Proceedings of ACCV.Google Scholar
  21. Kim, C., Li, F., Ciptadi, A., & Rehg, J. M. (2015). Multiple hypothesis tracking revisited. In Proceedings of ICCV.Google Scholar
  22. Lacoste-Julien, S., Taskar, B., Klein, D., & Jordan, M. I. (2006). Word alignment via quadratic assignment. In Proceedings of HLT-NAACL.Google Scholar
  23. Leal-Taixé, L., Fenzi, M., Kuznetsova, A., Rosenhahn, B., & Savarese, S. (2014). Learning an image-based motion context for multiple people tracking. In Proceedings of CVPR.Google Scholar
  24. Leal-Taixé, L., Milan, A., Reid, I., Roth, S., & Schindler, K. (2015). MOTChallenge 2015: Towards a benchmark for multi-target tracking. arXiv:1504.01942 [cs].
  25. Lenz, P., Geiger, A., & Urtasun, R. (2015). Followme: Efficient online min-cost flow tracking with bounded memory and computation. In Proceedings of ICCV.Google Scholar
  26. Li, Y., Huang, C., & Nevatia, R. (2009). Learning to associate: Hybridboosted multi-target tracker for crowded scene. In Proceedings of CVPR.Google Scholar
  27. Liu, C. (2009). Beyond pixels: Exploring new representations and applications for motion analysis. PhD Thesis, Massachusetts Institute of Technology.Google Scholar
  28. Lou, X., & Hamprecht, F. A. (2011). Structured learning for cell tracking. In Proceedings of NIPS.Google Scholar
  29. Milan, A., Leal-Taixé, L., Schindler, K., & Reid, I. (2015). Joint tracking and segmentation of multiple targets. In Proceedings of CVPR.Google Scholar
  30. Milan, A., Schindler, K., & Roth, S. (2012). Discrete–continuous optimization for multi-target tracking. In Proceedings of CVPR.Google Scholar
  31. Milan, A., Schindler, K., & Roth, S. (2013). Detection- and trajectory-level exclusion in multiple object tracking. In Proceedings of CVPR.Google Scholar
  32. Milan, A., Schindler, K., & Roth, S. (2016). Multi-target tracking by discrete–continuous energy minimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(10), 2054–2068.Google Scholar
  33. Milan, A., Roth, S., & Schindler, K. (2014). Continuous energy minimization for multitarget tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(1), 58–72.CrossRefGoogle Scholar
  34. Pirsiavash, H., Ramanan, D., & Fowlkes, C. C. (2011). Globally-optimal greedy algorithms for tracking a variable number of objects. In Proceedings of CVPR.Google Scholar
  35. Segal, A. V., & Reid, I. (2013). Latent data association: Bayesian model selection for multi-target tracking. In Proceedings of ICCV.Google Scholar
  36. Solera, F., Calderara, S., & Cucchiara, R. (2015). Learning to divide and conquer for online multi-target tracking. In Proceedings of ICCV.Google Scholar
  37. Szummer, M., Kohli, P., & Hoiem, D. (2008). Learning CRFs using graph cuts. In ECCV.Google Scholar
  38. Tang, S., Andres, B., Andriluka, M., & Schiele, B. (2015). Subgraph decomposition for multi-target tracking. In Proceedings of CVPR.Google Scholar
  39. Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., & Schiele, B. (2013). Learning people detectors for tracking in crowded scenes. In Proceedings of ICCV.Google Scholar
  40. Taskar, B., Guestrin, C., & Koller, D. (2003). Max-margin Markov networks. In Proceedings of NIPS.Google Scholar
  41. Wang, S., & Fowlkes, C. C. (2015). Learning optimal parameters for multi-target tracking. In Proceedings of BMVC.Google Scholar
  42. Wang, B., Wang, G., Luk Chan, K., & Wang, L. (2014). Tracklet association with online target-specific metric learning. In Proceedings of CVPR.Google Scholar
  43. Wang, X., Yang, M., Zhu, S., & Lin, Y. (2013). Regionlets for generic object detection. In Proceedings of ICCV.Google Scholar
  44. Wu, Z., Thangali, A., Sclaroff, S., & Betke, M. (2012). Coupling detection and data association for multiple object tracking. In Proceedings of CVPR.Google Scholar
  45. Xiang, Y., Alahi, A., & Savarese, S. (2015). Learning to track: Online multi-object tracking by decision making. In Proceedings of ICCV.Google Scholar
  46. Yang, B., & Nevatia, R. (2012). An online learned CRF model for multi-target tracking. In Proceedings of CVPR.Google Scholar
  47. Yoon, J. H., Yang, M., Lim, J., & Yoon, K. (2015). Bayesian multi-object tracking using motion context from multiple objects. In Proceedings of WACV.Google Scholar
  48. Zaied, A. N. H., & Shawky, L. A. E. (2014). A survey of quadratic assignment problems. International Journal of Computer Applications, 101(6), 28–36.Google Scholar
  49. Zhang, L., Li, Y., & Nevatia, R. (2008). Global data association for multi-object tracking using network flows. In Proceedings of CVPR.Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.Dept. of Computer ScienceUniversity of CaliforniaIrvineUSA

Personalised recommendations