Abstract
This paper proposes a novel visual tracking algorithm via online semi-supervised co-boosting, which investigates the benefits of co-boosting (i.e., the integration of co-training and boosting) and semi-supervised learning in the online tracking process. Existing discriminative tracking algorithms often use the classification results to update the classifier itself. However, the classification errors are easily accumulated during the self-training process. In this paper, we employ an effective online semi-supervised co-boosting framework to update the weak classifiers built on two different feature views. In this framework, the pseudo-label and importance of an unlabeled sample are estimated based on the additive logistic regression for an integration of a prior model and an online classifier learned on one feature view, and then used to update the weak classifiers built on the other feature view. The proposed algorithm has a good ability to recover from drifting by incorporating prior knowledge of the object while being adaptive to appearance changes by effectively combining the complementary strengths of different feature views. Experimental results on a series of challenging video sequences demonstrate the superior performance of our algorithm compared to state-of-the-art tracking algorithms.
Similar content being viewed by others
Notes
Code available at http://www.vision.ee.ethz.ch/boostingTrackers/download.html.
Code available at http://www.vision.ee.ethz.ch/boostingTrackers/download.html.
Code available at http://vision.ucsd.edu/~bbabenko/project_miltrack.shtml.
Code available at http://code.google.com/p/online-weighted-miltracker/.
Video sequences available at http://vision.ucsd.edu/~bbabenko/project_miltrack.shtml.
References
Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. (CSUR) 38(4), 1–45 (2006)
Yang, H., Shao, L., Zheng, F., Wang, L., Song, Z.: Recent advances and trends in visual tracking: a review. Neurocomputing 74, 3823–3831 (2011)
Ejaz, N., Baik, S.W.: Video summarization using a network of radial basis functions. Multimedia Syst. 18(6), 483–497 (2012)
Vondrick, C., Patterson, D., Ramanan, D.: Efficiently scaling up crowdsourced video annotation. Int. J. Comput. Vis. 101(1), 184–204 (2013)
Zhang, Z., Huang, K., Tan, T., Wang, Y.: 3D model based vehicle tracking using gradient based fitness evaluation under particle filter framework. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1771–1774 (2010)
Gardner, W.F., Lawton, D.T.: Interactive model-based vehicle tracking. IEEE Trans. Pattern Anal. Mach. Intell. 18(11), 1115–1121 (1996)
Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77(1), 125–141 (2008)
Ren, T., Qiu, Z., Liu, Y., Yu, T., Bei, J.: Soft-assigned bag of features for object tracking. Multimedia Syst. (2014). doi:10.1007/s00530-014-0384-y
Yoon, Y., Kosaka, A., Kak, A.C.: A new Kalman-filter-based framework for fast and accurate visual tracking of rigid objects. IEEE Trans. Robot. 24(5), 1238–1251 (2008)
Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust L1 tracker using accelerated proximal gradient approach. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1830–1837 (2012)
Avidan, S.: Support vector tracking. IEEE Trans. Pattern Anal. Mach. Intell. 26(8), 1064–1072 (2004)
Avidan, S.: Ensemble tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 494–501 (2005)
Grabner, H., Bischof, H.: On-line boosting and vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 260–267 (2006)
Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: British Machine Vision Conference (BMVC), pp. 47–56 (2006)
Oza, N., Russell, S.: Online bagging and boosting. In: International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 105–112 (2001)
Hare, S., Saffari, A., Torr, P.H.: Struck: structured output tracking with kernels. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 263–270 (2011)
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)
Zhang, K., Song, H.: Real-time visual tracking via online weighted multiple instance learning. Pattern Recognit. 46(1), 397–411 (2013)
Zhang, K., Zhang, L., Yang, M.H.: Real-time compressive tracking. In: European Conference on Computer Vision (ECCV), pp. 866–879 (2012)
Grabner, H., Leistner, C., Bischof, H.: Semi-supervised on-line boosting for robust tracking. In: European Conference on Computer Vision (ECCV), pp. 234–247 (2008)
Tang, F., Brennan, S., Zhao, Q., Tao, H.: Co-tracking using semi-supervised support vector machines. In: IEEE International Conference on Computer Vision (ICCV), pp. 1–8 (2007)
Liu, R., Cheng, J., Lu, H.: A robust boosting tracker with minimum error bound in a co-training framework. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1459–1466 (2009)
Ho, M.C., Chiang, C.C., Su, Y.Y.: Object tracking by exploiting adaptive region-wise linear subspace representations and adaptive templates in an iterative particle filter. Pattern Recognit. Lett. 33, 500–512 (2012)
Jiao, L., Wu, Y., Wu, G., Chang, E.Y., Wang, Y.: Anatomy of a multicamera video surveillance system. Multimedia Syst. 10(2), 144–163 (2004)
Leistner, C., Saffari, A., Roth, P., Bischof, H.: On robustness of on-line boosting—a competitive study. In: IEEE International Conference on Computer Vision (ICCV), pp. 1362–1369 (2009)
Kalal, Z., Matas, J., Mikolajczyk, K.: P-N learning: bootstrapping binary classifiers by structural constraints. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 49–56 (2010)
Zhang, K., Zhang, L., Yang, M.H.: Real-time compressive tracking, In: European Conference on Computer Vision (ECCV), pp. 866–879 (2012)
Rosenberg, C., Hebert, M., Schneiderman, H.: Semi-supervised self-training of object detection models. In: IEEE Workshop on Applications of Computer Vision (WACV), pp. 29–36 (2005)
Zhu, X.: Semi-supervised learning literature survey. In: Computer Sciences TR-1530. University of Wisconsin-Madison, USA (2007)
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Annual Conference on Computational Learning Theory (COLT), pp. 92–100 (1998)
Nigam, K., Ghani R.: Analyzing the effectiveness and applicability of co-training. In: ACM International Conference on Information and Knowledge Management (CIKM), pp. 86–93 (2000)
Balcan, M.F., Blum, A., Yang, K.: Co-training and expansion: Towards bridging theory and practice. In: Advances in Neural Information Processing Systems (NIPS), pp. 89–96 (2005)
Liu, C., Yuen, P.C.: A boosted co-training algorithm for human action recognition. IEEE Trans. Circ. Syst. Vid. 21(9), 1203–1213 (2011)
Mallapragada, P.K., Rong, J., Jain, A.K., Yi, L.: SemiBoost: boosting for semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 31(11), 2000–2014 (2009)
Leistner, C., Grabner, H., Bischof, H.: Semi-supervised boosting using visual similarity learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8 (2008)
Yang, Y., Zha, Z., Gao, Y.: Xiaofeng Zhu, Tat-Seng Chua, Exploiting web images for semantic video indexing via robust sample-specific loss. IEEE Trans. Multimedia 16(6), 1677–1689 (2014)
Yang, Y., Yang, Y., Shen, H.: Effective transfer tagging from image to video. ACM Trans. Multimedia Comput. Commun. Appl. 9(2), 14 (2013)
Pan, S., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Schapire, R.E., Rochery, M., Rahim, M., Gupta, N.: Incorporating prior knowledge into boosting. In: International Conference on Machine Learning (ICML), pp. 538–545 (2002)
Chen, S., Li, S., Su, S., Tian, Q., Ji, R.: Online MIL tracking with instance-level semi-supervised learning. Neurocomputing 139, 272–288 (2014)
Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. 28(2), 337–407 (2000)
Oza, N.: Online ensemble learning. Ph.D. thesis. University of California, Berkeley (2001)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: IEEE International Conference on Computer Vision (ICCV), pp. 511–518 (2001)
Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: application to face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 28(12), 2037–2041 (2006)
Welch, G., Bishop, G.: An introduction to the Kalman filter. Technical report. UNC-CH Computer Science Technical Report 95041 (1995)
Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2411–2418 (2013)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman A.: The PASCAL visual object classes challenge 2010 (VOC2010) results (2010)
Ying, L., Zhang, T., Xu, C.: Multi-object tracking via MHT with multiple information fusion in surveillance video. Multimedia Syst. (2014). doi:10.1007/s00530-014-0361-5
Acknowledgments
This work is supported by Xiamen University of Technology High Level Talents Project (No. YKJ14020R), the National Natural Science Foundation of China (Nos. 61373147 and 61201359), and the Natural Science Foundation of Fujian Province (No. 2012J05126).
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by T. Mei.
Rights and permissions
About this article
Cite this article
Chen, S., Zhu, S. & Yan, Y. Robust visual tracking via online semi-supervised co-boosting. Multimedia Systems 22, 297–313 (2016). https://doi.org/10.1007/s00530-015-0459-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-015-0459-4