Cong Zhang
ABSTRACT
Collective behaviors are usually composed of several groups. Considering the interactions among groups, this paper presents a novel framework to parse collective behaviors for video surveillance applications. We first propose a latent hierarchical model (LHM) with varying structure to represent the behavior with multiple groups. Furthermore, we also propose a multi-layer-based (MLB) inference method, where a sample-based heuristic search (SHS) is introduced to infer the group affiliation. And latent SVM is adopted to learn our model. With the proposed LHM, not only are the collective behaviors detected effectively, but also the group affiliation in the collective behaviors is figured out. Experiment results demonstrate the effectiveness of the proposed framework.
- BEHAVE data: http://homepages.inf.ed.ac.uk/rbf/BEHAVE.Google Scholar
- Yang Wang and G. Mori. Max-margin hidden conditional random fields for human action recognition. In Proc. CVPR, pages 872--879, June 2009.Google Scholar
- T. Do and T. Artières, "Large margin training for hidden markov models with partially observed states," Int'l Conf. Machine Learning (ICML), pp. 265--272, 2009. Google ScholarDigital Library
- D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564--574, 2003. Google ScholarDigital Library
- T. Lan, Y. Wang, W. Yang, S. Robinovitch, and G. Mori, "Discriminative latent models for recognizing contextual group activities," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 99, pp. 1--14, 2011. Google ScholarDigital Library
- W. Lin, M.-T. Sun, R. Poovendran, and Z. Zhang, "Group event detection with a varying number of group members for video surveillance," IEEE Trans. Circuits and Systems for Video Technology, vol. 20, no. 8, pp. 1057--067, 2010. Google ScholarDigital Library
- B. Ni, S. Yan, and A. Kassim, "Recognizing human group activities with localized causalities," IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1470--1477, 2009.Google Scholar
- C. Wang, J. Zhang, J. Pu, X. Yuan and L. Wang, "Chrono-gait image: A novel temporal template for gait recognition," Euro. Conf. Computer Vision (ECCV), pp. 257--270, 2010. Google ScholarDigital Library
- J. Yedidia, W.T. Freeman, and Y. Weiss, "Understanding belief propagation and its generalizations," Exploring artificial intelligence in the new millennium (G. Lakemeyer and B. Nebel eds.), chapter 8, pp. 236--239, 2003. Google ScholarDigital Library
- C. Yu and T. Joachims, "Learning structural SVMs with latent variables," Proc. ICML, pp. 1169--1176, 2009. Google ScholarDigital Library
- D. Zhang, D. Gatica-Perez, S. Bengio, and I. McCowan, "Modeling individual and group actions in meetings with layered HMMs," IEEE Trans. Multimedia, vol. 8, no. 3, pp. 509--520, 2006. Google ScholarDigital Library
- Y. Zhou, S. Yan, and T. Huang, "Pair-activity classification by bi-trajectories analysis," Proc. CVPR, pp. 1--8, 2008.Google Scholar
Index Terms
- Parsing collective behaviors by hierarchical model with varying structure
Recommendations
Accounting for patterns of collective behavior in crowd locomotor dynamics for realistic simulations
Transactions on Edutainment VIIDo people in a crowd behave like a set of isolated individuals or like a cohesive group? Studies of crowd modeling usually consider pedestrian behavior either from the point of view of an isolated individual or from that of large swarms. We introduce ...
Scalable Learning of Collective Behavior
This study of collective behavior is to understand how individuals behave in a social networking environment. Oceans of data generated by social media like Facebook, Twitter, Flickr, and YouTube present opportunities and challenges to study collective ...
Multi-objective Optimization of Multi-level Models for Controlling Animal Collective Behavior with Robots
Living Machines 2015: Proceedings of the 4th International Conference on Biomimetic and Biohybrid Systems - Volume 9222Group-living animals often exhibit complex collective behaviors that emerge through the non-linear dynamics of social interactions between individuals. Previous studies have shown that it is possible to influence the collective decision-making process ...
Comments