Motion Flow Tracking in Unconstrained Videos for Retail Scenario

详细信息    查看全文

• 作者：Eduardo Marques Pereira (19)
  Jaime S. Cardoso (19)
  Ricardo Morla (19)
  
• 关键词：optical flow ; trajectory analysis ; shopping behavior
• 刊名：Lecture Notes in Computer Science
• 出版年：2013
• 出版时间：2013
• 年：2013
• 卷：7887
• 期：1
• 全文大小：439KB
• 参考文献：1. (SBLX), S.B.X.: Axis cameras watch shopper’s behavior (2009), s.com/files/success_stories/ss_ret_sbxl_36113_en_0907_lo.pdf" class="a-plus-plus"> <span class="a-plus-plus emphasis fontcategory-non-proportional">http://www.axis.com/files/success_stories/ss_ret_sbxl_36113_en_0907_lo.pdf
  2. CUBEA: Cubea customer behavior analysis system (2006-2010), s/cubea.html" class="a-plus-plus"> <span class="a-plus-plus emphasis fontcategory-non-proportional">http://www.identrace.hu/products/cubea.html
  3. Popa, M., Rothkrantz, L., Yang, C.K., Wiggers, P., Braspenning, R., Shan, C.: Analysis of shopping behavior based on surveillance system. In: Dimirovski, G. (ed.) IEEE Int. Conf. on Systems and Man and and Cybernetics (SMC 2010), pp. 2512-519. Kudret Press, Instanbul (2010) ss="external" href="http://dx.doi.org/10.1109/ICSMC.2010.5641928">CrossRef
  4. Laptev, I.: On space-time interest points. Int. J. Comput. Vision?64(2-3), 107-23 (2005) ss="external" href="http://dx.doi.org/10.1007/s11263-005-1838-7">CrossRef
  5. Wang, H., Ullah, M.M., Kl?ser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. University of Central Florida, U.S.A (2009)
  6. Sun, J., Wu, X., Yan, S., Cheong, L.F., Chua, T.S., Li, J.: Hierarchical spatio-temporal context modeling for action recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2004-011 (2009)
  7. Lezama, J., Alahari, K., Sivic, J., Laptev, I.: Track to the future: Spatio-temporal video segmentation with long-range motion cues. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2011)
  8. Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol.?6315, pp. 282-95. Springer, Heidelberg (2010) ss="external" href="http://dx.doi.org/10.1007/978-3-642-15555-0_21">CrossRef
  9. Shi, J., Tomasi, C.: Good features to track. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, pp. 593-00 (June 1994)
  10. Farneb?ck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol.?2749, pp. 363-70. Springer, Heidelberg (2003) ss="external" href="http://dx.doi.org/10.1007/3-540-45103-X_50">CrossRef
  11. Brox, T., Malik, J.: Large displacement optical flow: Descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell.?33, 500-13 (2011) ss="external" href="http://dx.doi.org/10.1109/TPAMI.2010.143">CrossRef
  12. Ozturk, O., Yamasaki, T., Aizawa, K.: Detecting dominant motion flows in unstructured/structured crowd scenes. In: Proceedings of the 2010 20th International Conference on Pattern Recognition, ICPR 2010, pp. 3533-536. IEEE Computer Society, Washington, DC (2010)
  13. Eibl, G., Br?ndle, N.: Evaluation of clustering methods for finding dominant optical flow fields in crowded scenes. In: ICPR, pp. 1- (2008)
  14. Hu, M., Ali, S., Shah, M.: Detecting global motion patterns in complex videos. In: ICPR, pp. 1- (2008)
  15. Zhang, Z., Huang, K., Tan, T.: Comparison of similarity measures for trajectory clustering in outdoor surveillance scenes. In: Proceedings of the 18th International Conference on Pattern Recognition, ICPR 2006, vol.?3, pp. 1135-138. IEEE Computer Society, Washington, DC (2006)
  
• 作者单位：Eduardo Marques Pereira (19)
  Jaime S. Cardoso (19)
  Ricardo Morla (19)
  
  19. INESC TEC and Faculdade de Engenharia, Universidade do Porto, Portugal
  
• ISSN：1611-3349

文摘

We present a complete and modular framework that extract trajectories in a real and complex retail scenario, under unconstrained video conditions. Two motion tracking algorithms that combine features from crowd motion detection and multiple tracking are presented to build motion patterns and understand customer’s behavior. Their evaluation across several datasets show promising results.