Recognizing interactions between human performers by ‘Dominating Pose Doublet-

详细信息    查看全文

• 作者：Snehasis Mukherjee (1)
  Sujoy Kumar Biswas (2)
  Dipti Prasad Mukherjee (3)
  
• 关键词：Graph centrality ; Bag ; of ; words ; Human poses ; Interaction ; Dominating pose doublet ; Meaningfulness
• 刊名：Machine Vision and Applications
• 出版年：2014
• 出版时间：May 2014
• 年：2014
• 卷：25
• 期：4
• 页码：1033-1052
• 全文大小：1,876 KB
• 参考文献：1. Lan, T., Sigal, L.: Mori. G.Social roles in hierarchical models for human activity recognition. In: IEEE-CVPR, pp. 1355-362 (2012)
  2. Mukherjee, S., Biswas, S.K., Mukherjee, D.P.: Recognizing human action at a distance in video by key poses. IEEE T-CSVT 21(9), 1228-241 (2011)
  3. Narayan, B.L., Murthy, C.A., Pal, S.K.: Maxdiff kd-trees for data condensation. Pattern Recognit. Lett. 27(3), 187-00 (2006) CrossRef
  4. Yao, B., Fei-Fei, L.: Action recognition with exemplar based 2.5D graph matching. In: ECCV, LNCS 7575, pp. 173-86. Springer, Berlin (2012)
  5. Desolneux, A., Moisan, L., Morel, J.-M.: From Gestalt Theory to Image Analysis: A Probabilistic Approach. Springer, Berlin (2008) CrossRef
  6. Liu, J, Ali, S., Shah, M.: Recognizing human actions using multiple features. In: CVPR. IEEE Computer Society (2008)
  7. Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), 299-18 (2008) CrossRef
  8. Liu, C., Yuen, P.C.: Human action recognition using boosted eigenactions. Image Vis. Comput. 28(5), 825-35 (2010) CrossRef
  9. Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configurations: Combining segmentation and recognition. In: CVPR, vol. 2, pp. 326-33. IEEE Computer Society (2004)
  10. Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: ECCV, LNCS 2352, , vol. 3. pp. 666-80. Springer (2002)
  11. Han, D., Bo, L., Sminchisescu, C.: Selection and context for action recognition. In: ICCV, pp. 1933-940. IEEE Computer Society (2009)
  12. Wang, Y., Mori, G.: Hidden part models for human action recognition. Probabilistic vs. max-margin. IEEE T-PAMI 33(7), 1310-323 (2011) CrossRef
  13. Poppe, R.: Machine recognition of human activities: a survey. Image Vis. Comput. 28(6), 976-90 (2010) CrossRef
  14. Ryoo, M.S., Aggarwal, J.K., et al.: Human activity analysis: a review. ACM Comput. Sur. 43(3), 16:1-6:43 (2011)
  15. Wang, Y., Mori, G.: Human action recognition by semi-latent topic models. IEEE T-PAMI 31(10), 1762-774 (2009) CrossRef
  16. Ikizler, N., Duygulu, P.: Histogram of oriented rectangles: a new pose descriptor for human action recognition. Image Vis. Comput. 27(10), 1515-526 (2009) CrossRef
  17. Fengjun, L., Nevatia, R.: Single view human action recognition using key pose matching and viterbi path seraching. In: CVPR. IEEE Computer Society (2007)
  18. Du, Y., Chen, F., Xu, W.: Human interaction representation and recognition through motion decomposition. IEEE Signal Process. Lett. 14(12), 952-55 (2007) CrossRef
  19. Ryoo, M.S. , Aggarwal, J.K.: Spatio-temporal relationship match: video structure comparison for recognition of complex human activities. In: IEEE ICCV (2009)
  20. Ni, B., Pei, Y., Liang, Z., Lin, L., Moulin, P.: Integrating Multi-stage depth-induced contextual information for human action recognition and localization. In: IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, pp. 1- (2013)
  21. Patron-Perez, A., Marszalek, M., Zisserman, A., Reid, I.: High five: recognising human interactions in TV shows. In: British Machine Vision Conference (2010)
  22. Meng, L., Qing, L., Yang, P., Miao, J., Chen, X., Metaxas, D.N.: Activity recognition based on semantic spatial relation. In: International Conference on Pattern Recognition (IEEE-ICPR), pp. 609-12 (2012)
  23. Tang, K., Fei-Fei, Koller, D.: Learning latent temporal structure for complex event detection. In: IEEE-CVPR, pp. 1- (2012)
  24. Mukherjee, S., Biswas, S.K., Mukherjee, D.P.: Recognizing interaction between human performers using ‘key pose doublet- In: ACM Multimedia Conference, Arizona, pp. 1329-332. ACM (2011)
  25. Ryoo, M.S., Aggarwal, J.K.: UT-Interaction Dataset, ICPR contest on Semantic Description of Human Activities (SDHA). http://cvrc.ece.utexas.edu/SDHA2010/Human_Interaction.html. Accessed as on 2012
  26. Wolf, C. ,Mille, J., Lombardi, L.E, Celiktutan, O., Jiu, M., Baccouche, M., Dellandrea, E., Bichot, C., Garcia, C.-E., Sankur, B.: The LIRIS Human Activities Dataset and the ICPR 2012 Human Activities Recognition and Localization Competition. Technical Report RR-LIRIS-2012-004, LIRIS Laboratory (2012)
  27. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886-93. IEEE Computer Society (2005)
  28. Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms. MIT Press, Cambridge (2003)
  29. Navigli, R., Lapata, M.: An experimental study of graph connectivity for unsupervised word sense disambiguation. IEEE T-PAMI 32(4), 678-92 (2010) CrossRef
  30. Hoeffding, W.: Probability inequalities for sum of bounded random variables. J. Am. Stat. Assoc. 58(301), 13-0 (1963) CrossRef
  31. Varadhan, S.R.S.: Asymptotic probabilities and differential equations. Commun. Pure Appl. Math. 19(3), 261-86 (1966)
  32. Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers, pp. 61-4. MIT Press (1999)
  
• 作者单位：Snehasis Mukherjee (1)
  Sujoy Kumar Biswas (2)
  Dipti Prasad Mukherjee (3)
  
  1. Information Access Division, National Institute of Standards and Technology (NIST), 100 Bureau Drive, Gaithersburg, MD?, 20899-8940, USA
  2. Electrical Engineering Department, University of California, Santa Cruz, USA
  3. Electronics and Communication Sciences Unit, Indian Statistical Institute, 203 B.T. Road, Kolkata, 700108, India
  
• ISSN：1432-1769

文摘

A graph theoretic approach is proposed to recognize interactions (e.g., handshaking, punching, etc.) between two human performers in a video. Pose descriptors corresponding to each performer in the video are generated and clustered to form initial codebooks of human poses. Compact codebooks of dominating poses for each of the two performers are created by ranking the poses of the initial codebooks using two different methods. First, an average centrality measure of graph connectivity is introduced where poses are nodes in the graph. The dominating poses are graph nodes sharing a close semantic relationship with all other pose nodes and hence are expected to be at the central part of the graph. Second, a novel similarity measure is introduced for ranking dominating poses. The ‘pose doublets- all possible combinations of dominating poses of the two performers, are ranked using an improved centrality measure of a bipartite graph. The set of ‘dominating pose doublets-that best represents the corresponding interaction are selected using the perceptual analysis technique. The recognition results on standard interaction datasets show the efficacy of the proposed approach compared to the state-of-the-art.