Dual-Force Metric Learning for Robust Distracter-Resistant Tracker
Abstract
In this paper, we propose a robust distracter-resistant tracking approach by learning a discriminative metric that adaptively learns the importance of features on-the-fly. The proposed metric is elaborately designed for the tracking problem by forming a margin objective function which systematically includes distance margin maximization and reconstruction error constraint that acts as a force to push distracters away from the positive space and into the negative space. Due to the variety of negative samples in the tracking problem, we specifically introduce the similarity propagation technique that gives distracters a second force from the negative space. Consequently, the discriminative metric obtained helps to preserve the most discriminative information to separate the target from distracters while ensuring the stability of the optimal metric. We seamlessly combine it with the popular L1 minimization tracker. Our tracker is therefore not only resistant to distracters, but also inherits the merit of occlusion robustness from the L1 tracker. Quantitative comparisons with several state-of-the-art algorithms have been conducted in many challenging video sequences. The results show that our method resists distracters excellently and achieves superior performance.
Keywords
Visual tracking distracter distance metric similarity propagationReferences
- 1.Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: CVPR, pp. 798–805 (2006)Google Scholar
- 2.Avidan, S.: Ensemble tracking. TPAMI 29, 261–271 (2007)CrossRefGoogle Scholar
- 3.Babenko, B., Ming-Hsuan, Y., Belongie, S.: Visual tracking with online Multiple Instance Learning. In: CVPR, pp. 983–990 (2009)Google Scholar
- 4.Balan, A.O., Black, M.J.: An adaptive appearance model approach for model-based articulated object tracking. In: CVPR, pp. 758–765 (2006)Google Scholar
- 5.Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 15, 1373–1396 (2003)zbMATHCrossRefGoogle Scholar
- 6.Bian, W., Tao, D.: Biased discriminant Euclidean embedding for content-based image retrieval. TIP 19(2), 545–554 (2010)MathSciNetGoogle Scholar
- 7.Bogomolov, Y., Dror, G., Lapchev, S., Rivlin, E., Rudzsky, M.: Classification of moving targets based on motion and appearance. In: BMVC, pp. 429–438 (2003)Google Scholar
- 8.Cannons, K.J., Gryn, J.M., Wildes, R.P.: Visual Tracking Using a Pixelwise Spatiotemporal Oriented Energy Representation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 511–524. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 9.Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. TPAMI 27, 1631–1643 (2005)CrossRefGoogle Scholar
- 10.Dinh, T.B., Vo, N., Medioni, G.: Context tracker: Exploring supporters and distracters in unconstrained environments. In: CVPR, pp. 1177–1184 (2011)Google Scholar
- 11.Elgammal, A., Duraiswami, R., Davis, L.: Probabilistic tracking in joint feature spatial spaces. In: CVPR (2003)Google Scholar
- 12.Fan, J., Wu, Y., Dai, S.: Discriminative Spatial Attention for Robust Tracking. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 480–493. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 13.He, X., Cai, D., Yan, S., Zhang, H.J.: Neighborhood preserving embedding. In: ICCV, pp. 1208–1213 (2005)Google Scholar
- 14.Ho, J., Lee, K.C., Yang, M.H., Kriegman, D.: Visual tracking using learned linear subspaces. In: CVPR, pp. 782–789 (2004)Google Scholar
- 15.Jepson, A., Fleet, D., El-Maraghi, T.: Robust on-line appearance models for visual tracking. TPAMI 25, 1296–1311 (2003)CrossRefGoogle Scholar
- 16.Jiang, N., Liu, W., Wu, Y.: Adaptive and discriminative metric differential tracking. In: CVPR, pp. 1161–1168 (2011)Google Scholar
- 17.Kim, S.-J., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: A method for large-scale ℓ1-regularized least squares. IEEE Journal on Selected Topics in Signal Processing 1(4), 429–438 (2007)CrossRefGoogle Scholar
- 18.Kondor, R.I., Lafferty, J.: Diffusion kernels on graphs and other discrete input spaces. In: ICML, pp. 315–322 (2002)Google Scholar
- 19.Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR (2010)Google Scholar
- 20.Li, H., Shen, C., Shi, Q.: Real-time visual tracking using compressive sensing. In: CVPR, pp. 1305–1312 (2011)Google Scholar
- 21.Liu, B., Yang, L., Huang, J., Meer, P., Gong, L., Kulikowski, C.: Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 624–637. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 22.Liu, W., Tian, X., Tao, D., Liu, J.: Constrained metric learning via distance gap maximization. In: AAAI, pp. 518–524 (2010)Google Scholar
- 23.Mei, X., Ling, H.: Robust visual tracking using ℓ1 minimization. In: ICCV, pp. 1436–1443 (2009)Google Scholar
- 24.Mei, X., Ling, H., Wu, Y., Blasch, E., Bai, L.: Minimum error bounded efficient ℓ1 tracker with occlusion detection. In: CVPR, pp. 1257–1264 (2011)Google Scholar
- 25.Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. IJCV 77, 125–141 (2008)CrossRefGoogle Scholar
- 26.Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
- 27.Shi, J., Tomasi, C.: Good features to track. In: CVPR (1994)Google Scholar
- 28.Shrager, J., Hogg, T., Huberman, B.A.: Observation of phase transitions in spreading activation networks. Science 236, 1092–1094 (1987)CrossRefGoogle Scholar
- 29.Tao, D., Tang, X., Li, X., Rui, Y.: Direct kernel biased discriminant analysis: a new content-based image retrieval relevance feedback algorithm. IEEE Transactions on Multimedia 8(4), 716–727 (2006)CrossRefGoogle Scholar
- 30.Wang, X., Hua, G., Han, T.X.: Discriminative Tracking by Metric Learning. In: Daniilidis, K. (ed.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 200–214. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 31.Yu, Q., Dinh, T.B., Medioni, G.: Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 678–691. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 32.Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. In: NIPS, pp. 321–328 (2004)Google Scholar