Advertisement

Deep Learning of Appearance Models for Online Object Tracking

  • Mengyao ZhaiEmail author
  • Lei Chen
  • Greg Mori
  • Mehrsan Javan Roshtkhari
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11132)

Abstract

This paper introduces a deep learning based approach for vision based single target tracking. We address this problem by proposing a network architecture which takes the input video frames and directly computes the tracking score for any candidate target location by estimating the probability distributions of the positive and negative examples. An online fine-tuning step is carried out at every frame to learn the appearance of the target. The tracker has been tested on the standard tracking benchmark and the results indicate that the proposed solution achieves state-of-the-art tracking results.

References

  1. 1.
    Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 73–80. IEEE (2010)Google Scholar
  2. 2.
    Babenko, B., Yang, M.H., Belongie, S.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1619–1632 (2011)CrossRefGoogle Scholar
  3. 3.
    Dinh, T.B., Vo, N., Medioni, G.: Context tracker: exploring supporters and distracters in unconstrained environments. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1177–1184. IEEE (2011)Google Scholar
  4. 4.
    Hare, S., Saffari, A., Torr, P.: Struck: structured output tracking with kernels. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 263–270, November 2011.  https://doi.org/10.1109/ICCV.2011.6126251
  5. 5.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)CrossRefGoogle Scholar
  6. 6.
    Kalal, Z., Matas, J., Mikolajczyk, K.: P-N learning: bootstrapping binary classifiers by structural constraints. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 49–56. IEEE (2010)Google Scholar
  7. 7.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
  8. 8.
    Ma, C., Huang, J.B., Yang, X., Yang, M.H.: Hierarchical convolutional features for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3074–3082 (2015)Google Scholar
  9. 9.
    Qi, Y., et al.: Hedged deep tracking (2016)Google Scholar
  10. 10.
    Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3119–3127 (2015)Google Scholar
  11. 11.
    Wang, N., Li, S., Gupta, A., Yeung, D.Y.: Transferring rich feature hierarchies for robust visual tracking. arXiv preprint arXiv:1501.04587 (2015)
  12. 12.
    Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a Benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)Google Scholar
  13. 13.
    Yang, H., Shao, L., Zheng, F., Wang, L., Song, Z.: Recent advances and trends in visual tracking: a review. Neurocomputing 74(18), 3823–3831 (2011)CrossRefGoogle Scholar
  14. 14.
    Zhang, K., Zhang, L., Yang, M.H.: Real-time object tracking via online discriminative feature selection. IEEE Trans. Image Process. 22(12), 4664–4677 (2013)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mengyao Zhai
    • 1
    Email author
  • Lei Chen
    • 1
  • Greg Mori
    • 1
  • Mehrsan Javan Roshtkhari
    • 2
  1. 1.Simon Fraser UniversityBurnabyCanada
  2. 2.SPORTLOGiQMontrealCanada

Personalised recommendations