Locating and recognizing multiple human actions by searching for maximum score subsequences

详细信息    查看全文

• 作者：Hong-Bo Zhang (1) (2)
  Shao-Zi Li (1) (2)
  Shu-Yuan Chen (3)
  Song-Zhi Su (1) (2)
  Xian-Ming Lin (1) (2)
  Dong-Lin Cao (1) (2)
  
• 关键词：Multiple action recognition ; Frame ; based strategy ; Maximum score subsequences ; Contrast mutual information
• 刊名：Signal, Image and Video Processing
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：9
• 期：3
• 页码：705-714
• 全文大小：1,692 KB
• 参考文献：1. Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. 43(3):16:1鈥?6:43 (2011)
  2. Roppe, R.: A survey on vision-based human action recognition. Image Comput. 28(3), 976鈥?90 (2010)
  3. Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2鈥?), 107鈥?23 (2005) CrossRef
  4. Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: Proceedings 2rd International Workshop Visual Surveillance Performance Evaluation Tracking Surveillance, Beijing, China, Oct. 15鈥?6, pp. 65鈥?2 (2005)
  5. Wang, H., Ullah, M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: Presented at British Machine Vision Conference, London, England, Sept. 7鈥?0, (2009)
  6. Kl盲ser, A., Marsza艂ek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: Presented at British Machine Vision Conference. Leeds, UK, Sept. 1鈥?, (2008)
  7. Wang, Y., Mori, G.: Learning a discriminative hidden part model for human action recognition. In: Proceedings 22nd Annual Conference on Neural Information Processing Systems, Vancouver, Canada, Dec. 8鈥?1, pp. 1721鈥?728 (2008)
  8. Jhuang, H., Serre, T., Wolf, L., Poggio, T.: A biologically inspired system for action recognition. In: Proceedings International Conference Computer Vision, Rio de Janeiro, Brazil, Oct. 14鈥?1, pp. 1鈥? (2007)
  9. Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings 15th ACM International Conference Multimedia, Bavaria, Germany, Sept. 24鈥?9, pp. 357鈥?60 (2007)
  10. Laptev, I., Lindeberg, T.: Local descriptors for spatio-temporal recognition. In: Proceedings International Workshop on Spatial Coherence for Visual Motion Analysis, Prague, Czech republic, May 15鈥?5, pp. 91鈥?03 (2004)
  11. Laptev, I., Marsza艂ek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings 26th IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, United states, Jun. 23鈥?8, pp. 1鈥? (2008)
  12. Willems, G., Tuytelaars, T., Van Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Proceedings 10th European Conference on Computer Vision, Marseille, France, Oct. 12鈥?8, pp. 650鈥?63 (2008)
  13. Yuan, J., Liu, S., Wu, Y.: Discriminative video pattern search for efficient action detection. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1728鈥?743 (2011)
  14. Niebles, J.C., Wang, H., Li, F.-F.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), 299鈥?18 (2008) CrossRef
  15. Bently, J.: Programming pearls: algorithm design techniques. Commun. ACM 27(9), 865鈥?73 (1984) CrossRef
  16. http://www.nada.kth.se/cvap/actions/
  17. Zhang, T., Liu, J., Liu, S., Xu, C., Lu, H.: Boosted exemplar learning for action recognition and annotation. IEEE Trans. Circuits Syst. Video Technol. 21(7), 853鈥?66 (2011) CrossRef
  18. Seo, H.J., Milanfar, P.: Action recognition from one example. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 867鈥?82 (2011) CrossRef
  19. Chakraborty, B., Holte, M., Moeslund, T.B., Gonzalez, J.: Selective spatio-temporal interest points. Comput. Vis. Image Underst. 116(3), 396鈥?10 (2012) CrossRef
  
• 作者单位：Hong-Bo Zhang (1) (2)
  Shao-Zi Li (1) (2)
  Shu-Yuan Chen (3)
  Song-Zhi Su (1) (2)
  Xian-Ming Lin (1) (2)
  Dong-Lin Cao (1) (2)
  
  1. School of Information Science and Technology, Xiamen University, Xiamen, China
  2. Fujian Key Laboratory of the Brain-like Intelligent Systems, Xiamen University, Xiamen, China
  3. Department of Computer Science and Engineering, Yuan Ze University, Taoyuan, Taiwan
  
• 刊物类别：Engineering
• 刊物主题：Signal,Image and Speech Processing
  Image Processing and Computer Vision
  Computer Imaging, Vision, Pattern Recognition and Graphics
  Multimedia Information Systems
  
• 出版者：Springer London
• ISSN：1863-1711

文摘

Despite the numerous methods to recognize human actions in a video, few are designed for videos containing more than one action over a certain time period. Moreover, existing multiple action recognition methods adopt windowed sequence search strategy. Windowed sequence searching requires an exhaustive trial of window length yielding intensive computation. This work presents a frame-based strategy, capable of searching for maximum score subsequences that correspond to actions. Therefore, start and ending times of all actions are located, and action categories are identified as well. Moreover, contrast mutual information is proposed as a new score function to increase recognition accuracy. Experimental results indicate that the proposed method locates and recognizes multiple actions in a video accurately, even for the conventional single action classification problem.