Orderless and Blurred Visual Tracking via Spatio-temporal Context

详细信息    查看全文

• 作者：Manna Dai (19)
  Peijie Lin (19)
  Lijun Wu (19)
  Zhicong Chen (19)
  Songlin Lai (19)
  Jie Zhang (19)
  Shuying Cheng (19)
  Xiangjian He (20)
  
• 关键词：spatio ; temporal ; context ; resize ; Euclidean Distance ; Bayesian framework
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：8935
• 期：1
• 页码：25-36
• 全文大小：3,164 KB
• 参考文献：1. Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Computing Surveys (CSUR)?38(4) (2006)
  2. Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR, pp. 1269-276 (2010)
  3. Kwon, J., Lee, K.M.: Tracking by sampling trackers. In: ICCV, pp. 1195-202 (2011)
  4. Oron, S., Bar-Hillel, A., Levi, D., Avidan, S.: Locally orderless tracking. In: CVPR, pp. 1940-947 (2012)
  5. Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol.?7574, pp. 864-77. Springer, Heidelberg (2012) CrossRef
  6. Hare, S., Saffari, A., Torr, P.H.: Struck: Structured output tracking with kernels. In: ICCV, pp. 263-70 (2011)
  7. Zhang, K., Song, H.: Real-time visual tracking via online weighted multiple instance learning. Pattern Recognition (2012)
  8. Zhang, K., Zhang, L., Liu, Q., Zhang, D., Yang, M.-H.: Fast visual tracking via dense spatio-temporal context learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol.?8693, pp. 127-41. Springer, Heidelberg (2014) CrossRef
  9. Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. IEEE TPAMI?34(11) (2012)
  10. Heitz, G., Koller, D.: Learning spatial context: Using stuff to find things. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol.?5302, pp. 30-3. Springer, Heidelberg (2008) CrossRef
  11. Cheng, M.-M., Zhang, Z., Lin, W.-Y., Torr, P.: Bing: Binarized Normed Gradients for objectness estimation at 300fps. In: CVPR (2004)
  12. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol.?1, pp. 886-93 (2005)
  13. Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained partbased models. IEEE TPAMI?32(9), 1672-645 (2010)
  14. Oppenheim, A.V., Willsky, A.S., Nawab, S.H.: Signals and systems, vol.?2. Prentice-Hall, Englewood Cliffs (1983)
  15. Bolme, D.S., Draper, B.A., Beveridge, J.R.: Average of synthetic exact filters. In: CVPR, pp. 2105-112 (2009)
  16. Zhang, K., Song, H.: Real-time visual tracking via online weighted multiple instance learning. Pattern Recognition (2012)
  17. Ross, D.A., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. International Journal of Computer Vision?77(1-3), 125-41 (2008) CrossRef
  18. Mei, X., Ling, H.: Robust visual tracking using 1 minimization. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1436-443. IEEE (2009)
  19. Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust L1 tracker using accelerated proximal gradient approach. In: CVPR (2012)
  20. Danelljan, M., Khan, F.S., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR, pp. 1090-097 (2014)
  21. Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: A benchmark. In: CVPR (2013)
  
• 作者单位：Manna Dai (19)
  Peijie Lin (19)
  Lijun Wu (19)
  Zhicong Chen (19)
  Songlin Lai (19)
  Jie Zhang (19)
  Shuying Cheng (19)
  Xiangjian He (20)
  
  19. Institute of Micro/ Nano Devices and Solar Cells, College of Physics and Information Engineering, Fuzhou University, Fuzhou, 350108, China
  20. Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia
  
• ISSN：1611-3349

文摘

In this paper, a novel and robust method which exploits the spatiotemporal context for orderless and blurred visual tracking is presented. This lets the tracker adapt to both rigid and deformable objects on-line even if the image is blurred. We observe that a RGB vector of an image which is resized into a small fixed size can keep enough useful information. Based on this observation and computational reasons, we propose to resize the windows of both template and candidate target images into 2×2 and use Euclidean Distance to compute the similarity between these two RGB image vectors for the preliminary screening. We then apply spatio-temporal context based on Bayesian framework to further compute a confidence map for obtaining the best target location. Experimental results on challenging video sequences in MATLAB without code optimization show the proposed tracking method outperforms eight state-of-the-art methods.