access icon free Compact discriminative object representation via weakly supervised learning for real-time visual tracking

Object representations are of great importance for robust visual tracking. Although the high-dimensional representation can effectively encode the input data with more information, exploiting it in a real-time tracking system would be intractable and infeasible due to the high computational cost and memory requirements. In this study, the authors propose a compact discriminative object representation to achieve both good tracking accuracy and efficiency. An ensemble of weak training sets is generated based on the self-representative ability of tracking samples, which is applied to learn discriminative functions. Each candidate is represented by the concatenation of project values on all the weak training sets. Tracking is then carried out within a Bayesian inference framework where the classification score of the support vector machine is used to construct the observation model. The evaluations on TB50 benchmark dataset demonstrate that the proposed algorithm is much more computationally efficient than the state-of-the-art methods with comparable accuracy.

Inspec keywords: Bayes methods; image classification; inference mechanisms; real-time systems; object tracking; support vector machines; learning (artificial intelligence)

Other keywords: classification score; real-time visual tracking; weakly supervised learning; support vector machine; Bayesian inference framework; computational efficiency; real-time tracking system; object representation learning

Subjects: Other topics in statistics; Knowledge engineering techniques; Image recognition; Other topics in statistics; Computer vision and image processing techniques

References

    1. 1)
      • 27. Wang, L., Ouyang, W., Wang, X., et al: ‘Visual tracking with fully convolutional networks’. Proc. IEEE Int. Conf. Computer Vision (ICCV), 2015, pp. 31193127.
    2. 2)
      • 41. Danelljan, M., Shahbaz Khan, F., Felsberg, M., et al: ‘Adaptive color attributes for real-time visual tracking’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2014, pp. 10901097.
    3. 3)
      • 17. Yang, X., Wang, S.: ‘Fast deformable structure regression tracking’, IET Comput. Vis., 2016, 10, (2), pp. 115123.
    4. 4)
      • 12. Ma, L., Zhang, X., Hu, W., et al: ‘Local subspace collaborative tracking’. IEEE Int. Conf. Computer Vision (ICCV), 2015, pp. 43014309.
    5. 5)
      • 24. Wang, L., Ouyang, W., Wang, X., et al: ‘Stct: sequentially training convolutional networks for visual tracking’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 13731381.
    6. 6)
      • 40. Wu, Y., Ma, B., Yang, M., et al: ‘Metric learning based structural appearance model for robust visual tracking’, IEEE Trans. Circuits Syst. Video Technol., 2014, 24, (5), pp. 865877.
    7. 7)
      • 31. Fan, H., Xiang, J.: ‘Robust visual tracking with multitask joint dictionary learning’, IEEE Trans. Circuits Syst. Video Technol., 2017, 27, (5), pp. 10181030.
    8. 8)
      • 19. Tang, M., Feng, J.: ‘Multi-kernel correlation filter for visual tracking’. IEEE Int. Conf. Computer Vision (ICCV), 2015, pp. 30383046.
    9. 9)
      • 16. Ning, J., Yang, J., Jiang, S., et al: ‘Object tracking via dual linear structured SVM and explicit feature map’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 42664274.
    10. 10)
      • 14. Ross, D.A., Lim, J., Lin, R.S., et al: ‘Incremental learning for robust visual tracking’, Int. J. Comput. Vis., 2008, 77, (1-3), pp. 125141.
    11. 11)
      • 32. Henriques, J.F., Caseiro, R., Martins, P., et al: ‘High-speed tracking with kernelized correlation filters’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (3), pp. 583596.
    12. 12)
      • 8. Liu, T., Wang, G., Yang, Q.: ‘Real-time part-based visual tracking via adaptive correlation filters’. IEEE Int. Conf. Computer Vision (ICCV), 2015, pp. 49024912.
    13. 13)
      • 38. Kwon, J., Lee, K.M.: ‘Visual tracking decomposition’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2010, pp. 12691276.
    14. 14)
      • 29. Wang, N., Yeung, D.Y.: ‘Learning a deep compact image representation for visual tracking’. Advances in Neural Information Processing Systems (NIPS), 2013, pp. 809817.
    15. 15)
      • 34. Zhu, P., Zuo, W., Zhang, L., et al: ‘Unsupervised feature selection by regularized self-representation’, Pattern Recognit., 2015, 48, (2), pp. 438446.
    16. 16)
      • 4. Zhang, T., Jia, K., Xu, C., et al: ‘Partial occlusion handling for visual tracking via robust part matching’. Proc. of IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2014, pp. 12581265.
    17. 17)
      • 7. Li, W., Wen, L., Chuah, M.C., et al: ‘Online visual tracking using temporally coherent part cluster’. IEEE Workshop on Applications of Computer Vision (WACV), 2015, pp. 916.
    18. 18)
      • 13. Mei, X., Ling, H.: ‘Robust visual tracking using L1 minimization’. IEEE Int. Conf. Computer Vision (ICCV), 2009, pp. 14361443.
    19. 19)
      • 22. Yao, R., Shi, Q., Shen, C., et al: ‘Part-based visual tracking with online latent structural learning’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2013, pp. 23632370.
    20. 20)
      • 42. Wang, N., Wang, J., Yeung, D.Y.: ‘Online robust non-negative dictionary learning for visual tracking’. IEEE Int. Conf. Computer Vision (ICCV), 2013, pp. 657664.
    21. 21)
      • 21. He, Y., Pei, M., Yang, M., et al: ‘Online visual tracking by integrating spatiotemporal cues’, IET Comput. Vis., 2015, 9, (1), pp. 124137.
    22. 22)
      • 26. Ma, C., Huang, J.B., Yang, X., et al: ‘Hierarchical convolutional features for visual tracking’. Proc. IEEE Int. Conf. Computer Vision (ICCV), 2015, pp. 30743082.
    23. 23)
      • 1. Li, X., Hu, W., Shen, C., et al: ‘A survey of appearance models in visual object tracking’, ACM Trans. Intell. Syst. Technol. (TIST), 2013, 4, (4), p. 58.
    24. 24)
      • 33. Elhamifar, E., Sapiro, G., Vidal, R.: ‘See all by looking at a few: Sparse modeling for finding representative objects’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2012, pp. 16001607.
    25. 25)
      • 39. Zhong, W., Lu, H., Yang, M.H.: ‘Robust object tracking via sparsity-based collaborative model’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2012, pp. 18381845.
    26. 26)
      • 23. Hare, S., Saffari, A., Torr, P.H.: ‘Struck: structured output tracking with kernels’. IEEE Int. Conf. Computer Vision (ICCV) IEEE, 2011, pp. 263270.
    27. 27)
      • 6. Jia, X., Lu, H., Yang, M.H.: ‘Visual tracking via adaptive structural local sparse appearance model’. Proc. of IEEE Conf. Computer vision and pattern recognition (CVPR), 2012, pp. 18221829.
    28. 28)
      • 11. Sui, Y., Tang, Y., Zhang, L.: ‘Discriminative low-rank tracking’. IEEE Int. Conf. Computer Vision (ICCV), 2015, pp. 30023010.
    29. 29)
      • 20. Kalal, Z., Mikolajczyk, K., Matas, J.: ‘Tracking-learning-detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (7), pp. 14091422.
    30. 30)
      • 37. Kozakaya, T., Ito, S., Kubota, S.: ‘Random ensemble metrics for object recognition’. IEEE Int. Conf. Computer Vision (ICCV), 2011. pp. 19591966.
    31. 31)
      • 2. Wu, Y., Lim, J., Yang, M.H.: ‘Object tracking benchmark’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (9), pp. 18341848.
    32. 32)
      • 30. Zhang, K., Liu, Q., Wu, Y., et al: ‘Robust visual tracking via convolutional networks without training’, IEEE Trans. Image Process., 2016, 25, (4), pp. 17791792.
    33. 33)
      • 5. Zhong, W., Lu, H., Yang, M.H.: ‘Robust object tracking via sparse collaborative appearance model’, IEEE Trans. Image Process., 2014, 23, (5), pp. 23562368.
    34. 34)
      • 10. Li, X., Shen, C., Dick, A., et al: ‘Online metric-weighted linear representations for robust visual tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2016, 38, (5), pp. 931950.
    35. 35)
      • 18. Wu, Y., Pei, M., Yang, M., et al: ‘Robust discriminative tracking via landmark-based label propagation’, IEEE Trans. Image Process., 2015, 24, (5), pp. 15101523.
    36. 36)
      • 36. Gharbi, M., Malisiewicz, T., Paris, S., et al: ‘A Gaussian approximation of feature space for fast image similarity’. Technical Report 2012–032, MIT CSAIL, 2012.
    37. 37)
      • 35. Dai, D., Van Gool, L.: ‘Ensemble projection for semi-supervised image classification’. IEEE Int. Conf. Computer Vision (ICCV), 2013, pp. 20722079.
    38. 38)
      • 3. Li, A., Lin, M., Wu, Y., et al: ‘Nus-pro: a new visual tracking challenge’, IEEE Trans. Pattern Anal. Mach. Intell., 2016, 38, (2), pp. 335349.
    39. 39)
      • 9. Zhang, L., Lu, H., Du, D., et al: ‘Sparse hashing tracking’, IEEE Trans. Image Process., 2016, 25, (2), pp. 840849.
    40. 40)
      • 28. Li, H., Li, Y., Porikli, F.: ‘Robust online visual tracking with a single convolutional neural network’. Proc. Asian Conf. Computer Vision (ACCV), 2014, pp. 194209.
    41. 41)
      • 15. Wang, Q., Chen, F., Yang, J., et al: ‘Transferring visual prior for online object tracking’, IEEE Trans. Image Process., 2012, 21, (7), pp. 32963305.
    42. 42)
      • 25. Qi, Y., Zhang, S., Qin, L., et al: ‘Hedged deep tracking’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 43034311.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0287
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0287
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading