Abstract
This paper proposes a method to deal with long-term robust object tracking in unconstrained environment. The approach exploits both target and background information on the fly automatically. It builds the structural constraint using active context learning to enhance the adaptability for variation of the target and stability of tracking. An optical-flow-based motion region extraction method is integrated into the context learning framework to address the problem of fast target motion or abrupt camera motion. Experimental results on challenging real-world video sequences demonstrate the effectiveness and robustness of our approach. Comparisons with several state-of-the-art methods are provided.
Similar content being viewed by others
References
Isard, M., Blake, A.: CONDENSATION—Conditional density propagation for visual tracking. Int’l J. Comput. Vis. (IJCV) 29, 5–28 (1998)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25(5), 564–577 (May 2003)
Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. 38(4), 13 (Dec. 2006)
Avidan, S.: Ensemble tracking. IEEE Trans. Pattern Anal. Mach. Intell. 29(2), 261–271 (2007)
Collins, R., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1631–1643 (2005)
Lim, J., Ross, D., Lin, R., Yang, M.: Incremental learning for visual tracking. Neural Inf. Process. Systems (NIPS) (2005)
Grabner, H., Bischof, H.: On-line boosting and vision. IEEE Conf. Comput. Vis. Pattern Recogn. (CVPR) 1, 260–267 (2006)
Saffari, A., Leistner, C., Santner, J., Godec, M., Bischof, H.: On-line random forests. IEEE Int’l Conf, Computer Vision (ICCV), WS on On-line Learning for Computer Vision (2009)
Wang, A., Wan, G., Cheng, Z., Li, S.: An incremental extremely random forest classifier for online learning and tracking. IEEE Int’l Conf. Image Processing (ICIP), pp. 1449–1452 (2009)
Grabner, H., Leistner, C., Bischof, H.: Semi-supervised on-line boosting for robust tracking. European Conference on Computer Vision (ECCV) (2008)
Stalder, S., Grabner, H., van Gool, L., Zurich, E., Leuven, K.: Beyond semi-supervised tracking: tracking should be as simple as detection, but not simpler than recognition. IEEE Int’l Conf, Computer Vision (ICCV), WS on On-line Learning for Computer Vision (2009)
Leistner, C., Saffari, A., Santner, J., Bischof, H.: Semi-supervised random forests. IEEE Int’l Conf, Computer Vision (ICCV) (2009)
Leistner, C., Godec, M., Saffari, A., Bischof, H.: On-line multi-view forests for tracking. DAGM-Symposium, pp. 493–502 (2010)
Chapelle, O., Scholkopf, B., Zien, A. (eds.): Semi-Supervised Learning. MIT Press, Cambridge, MA (2006)
Babenko, B., Yang, M.-H., Belongie, S.: Visual tracking with online multiple instance learning. IEEE Conf, Computer Vision and Pattern Recognition (CVPR) (2009)
Leistner, C., Saffari, A., Bischof, H.: MILForests: multiple-instance learning with randomized trees. European Conference on Computer Vision (ECCV) (2010).
Yu, Q., Dinh, T., Medioni, G.: Online tracking and reacquisition using co-trained generative and discriminative trackers. European Conference on Computer Vision (ECCV) (2008)
Kalal, Z., Matas, J., Mikolajczyk, K.: Online learning of robust object detectors during unstable tracking. IEEE Int’l Conf, Computer Vision (ICCV), WS on On-line Learning for Computer Vision (2009)
Kalal, Z., Matas, J., Mikolajczyk, K.: P-N learning: bootstrapping binary classifiers by structural constraints. IEEE Conf, Computer Vision and Pattern Recognition (CVPR) (2010)
Zhong, W., Lu, H., Yang, M.: Robust object tracking via sparsity-based collaborative model. IEEE Conf, Computer Vision and Pattern Recognition (CVPR) (2012)
Yang, M., Wu, Y., Hua, G.: Context-aware visual tracking. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1195–1209 (2009)
Grabner, H., Matas, J., Gool, L.V., Cattin, P.: Tracking the invisible: learning where the object might be. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1285–1292 (2010).
Dinh, T.B., Vo, N., Medioni, G.: Context tracker: exploring supporters and distracters in unconstrained environments. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1177–1184 (2011).
Fan, J., Wu, Y., Dai, S.: Discriminative spatial attention for robust tracking. European Conference on Computer Vision (ECCV), pp. 480–493 (2010).
Godec, M., Sternig, S., Roth, P.M., Bischof, H.: Context-driven clustering by multi-class classification in an active learning framework. IEEE Conf. Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 19–24 (2010).
Shakhnarovich, G., Darrell, T., Indyk, P.: Nearest-Neighbor Methods in Learning and Vision: Theory and Practice, MIT Press, Cambridge (2005).
Stenger, B., Woodley, T., Cipolla, R.: Learning to track with multiple observers. IEEE Conf, Computer Vision and Pattern Recognition (CVPR), Miami (2009)
Ozuysal, M., Fua, P., Lepetit, V.: Fast keypoint recognition in ten lines of code. IEEE Conf, Computer Vision and Pattern Recognition (CVPR) (2007)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. IEEE Conf, Computer Vision and Pattern Recognition (CVPR) (2001)
Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. Pattern Anal. Mach. Intell (2004).
Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 798–805 (2006)
Acknowledgments
This work was supported by the fundamental research funds for the Central Universities of China (Grant No. 2682014cx024 and SWJTU12BR024).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Quan, W., Jiang, Y., Zhang, J. et al. Robust object tracking with active context learning. Vis Comput 31, 1307–1318 (2015). https://doi.org/10.1007/s00371-014-1012-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-014-1012-8