Visual Tracking via Sparse Representation and Online Dictionary Learning

详细信息    查看全文

• 作者：Xu Cheng (16)
  Nijun Li (16)
  Tongchi Zhou (16)
  Lin Zhou (16)
  Zhenyang Wu (16)
  
• 关键词：Multiple objects tracking ; Sparse representation ; Online dictionary learning ; Appearance model ; L1 minimization
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：1
• 期：1
• 页码：87-103
• 全文大小：6,329 KB
• 参考文献：1. Ross, D., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. IJCV 77(1), 125鈥?41 (2008) CrossRef
  2. Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR, pp. 1269鈥?276 (2010)
  3. Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: BMVC, pp. 47鈥?6 (2006)
  4. Babenko, B., Yang, M., Belongie, S.: Visual tracking with online multiple instance learning. IEEE Trans. PAMI 33(8), 1619鈥?632 (2011) CrossRef
  5. Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. PAMI 31(2), 210鈥?27 (2009) CrossRef
  6. Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. IEEE Trans. PAMI 33(11), 2259鈥?272 (2011) CrossRef
  7. Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust L1 tracker using accelerated proximal gradient approach. In: CVPR, pp. 1830鈥?837 (2012)
  8. Liu, B., Huang, J., Yang, L., Kulikowsk, C.: Robust tracking using local sparse appearance model and k-selection. In: CVPR, pp. 1313鈥?320 (2011)
  9. Zhong, W., Lu, H., Yang, M.: Robust object tracking via sparsity-based collaborative model. In: CVPR, pp. 1鈥? (2012)
  10. Jia, X., Lu, H., Yang, M.H.: Visual tracking via adaptive structural local sparse appearance model. In: CVPR, pp. 1822鈥?829 (2012)
  11. Zhang, X., Li, W., Hu, W., et al.: Block covariance based L1 tracker with a subtle template dictionary. Pattern Recogn. 46(7), 1750鈥?761 (2013). (Special Issue: Sparse representation for event recognition in video surveillance) CrossRef
  12. Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: Robust visual tracking via structured multi-task sparse learning. IJCV 101(2), 367鈥?83 (2013) CrossRef
  13. Li, H., Shen, C., Shi, Q.: Real-time visual tracking with compressed sensing. In: CVPR, pp. 1305鈥?312 (2011)
  14. Zhang, S., Yao, H., Sun, X., Lu, X.: Sparse coding based visual tracking: review and experimental comparison. Pattern Recogn. 46(7), 1772鈥?788 (2013) CrossRef
  15. Lu, W., Okuma, K., Little, J.: Tracking and recognizing actions of multiple hockey players using the boosted particle filter. Image Vis. Comput. 27, 189鈥?05 (2009) CrossRef
  16. Breitenstein, M., Reichlin, F., Leibe, B., Koller-Meier, E., Gool, L.V.: Online multiperson tracking-by-detection from a single, uncalibrated camera. IEEE Trans. PAMI 33(9), 1820鈥?833 (2011) CrossRef
  17. Yang, B., Huang, C., Nevatia, R.: Learning affinities and dependencies for multi-target tracking using a CRF model. In: CVPR, pp. 1233鈥?240 (2011)
  18. Kuo, C., Huang, C., Nevatia, R.: Multi-target tracking by on-line learned discriminative appearance models. In: CVPR, pp. 685鈥?92 (2010)
  19. Berclaz, J., Fleuret, F., Turetken, E., Fua, P.: Multiple object tracking using k-shortest paths optimization. IEEE Trans. PAMI 33(9), 1806鈥?819 (2011) CrossRef
  20. Huang, C., Wu, B., Nevatia, R.: Robust object tracking by hierarchical association of detection responses. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 788鈥?01. Springer, Heidelberg (2008) CrossRef
  21. Jiang, H., Fels, S., Little, J.: A linear programming approach for multiple object tracking. In: CVPR, pp. 1鈥? (2007)
  22. Kuo, C.H., Nevatia, R.: How does person identity recognition help multi-person tracking? In: CVPR, pp. 1217鈥?224 (2011)
  23. Milan, A., Roth, S., Schindler, K.: Continuous energy minimization for multitarget tracking. IEEE Trans. PAMI 36(1), 58鈥?2 (2014) CrossRef
  24. Pirsiavash, H., Ramanan, D., Fowlkes, C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR, pp. 1201鈥?208 (2011)
  25. Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. PAMI 34(7), 1409鈥?422 (2012) CrossRef
  26. Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91鈥?10 (2004) CrossRef
  27. Szummer, M., Kohli, P., Hoiem, D.: Learning CRFs using graph cuts. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 582鈥?95. Springer, Heidelberg (2008) CrossRef
  28. Yang, J., Yang, M.H.: Top-down visual saliency via joint CRF and dictionary learning. In: CVPR, pp. 2296鈥?303 (2012)
  29. Lozano, A.C., Swirszcz, G., Abe, N.: Group orthogonal matching pursuit for variable selection and prediction. In: NIPS (2009)
  30. Yang, J., Yu, K., Huang, T.: Supervised translation-invariant sparse coding. In: CVPR (2010)
  31. Cheng, X., Li, N., Zhang, S., et al.: Robust visual tracking with SIFT features and fragments based on particle swarm optimization. Circuits Syst. Signal Process. 33(5), 1507鈥?526 (2014) CrossRef
  32. Yoon, J.H., Kim, D.Y., Yoon, K.-J.: Visual tracking via adaptive tracker selection with multiple features. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 28鈥?1. Springer, Heidelberg (2012) CrossRef
  33. Wang, X., T眉retken, E., Fleuret, F., Fua, P.: Tracking interacting objects optimally using integer programming. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 17鈥?2. Springer, Heidelberg (2014) CrossRef
  34. Joachims, T., Finley, T., Yu, C.: Cutting-plane training of structural SVM. Mach. Learn. 77(1), 27鈥?9 (2009) CrossRef
  
• 作者单位：Xu Cheng (16)
  Nijun Li (16)
  Tongchi Zhou (16)
  Lin Zhou (16)
  Zhenyang Wu (16)
  
  16. School of Information Science and Engineering, Southeast University, Nanjing, 210096, China
  
• ISSN：1611-3349

文摘

Sparse representation has been shown competitive performance on single object tracking. In this paper, we extend this technique to tracking multiple interactive objects and present a novel sparse tracker under the tracking-by-detection framework, with saliency detector for objects detection and sparse representation for objects association. Furthermore, we propose an online dictionary learning scheme to capture appearance variations of objects. To avoid using trivial templates, the dictionary contains not only objects templates, but also background information, resulting in more robust estimation. The experiments demonstrate that our approach achieves favorable performance over state-of-the-art algorithms.