论文信息 - Graphical Models for Recognizing Human Interactions

Graphical Models for Recognizing Human Interactions

We describe a real-time computer vision and machine learning system for modeling and recognizing human actions and interactions. Two different domains are explored: recognition of two-handed motions in the martial art 'Tai Chi', and multiple-person interactions in a visual surveillance task. Our system combines top-down with bottom-up information using a feedback loop, and is formulated with a Bayesian framework. Two different graphical models (HMMs and Coupled HMMs) are used for modeling both individual actions and multiple-agent interactions, and CHMMs are shown to work more efficiently and accurately for a given amount of training. Finally, to overcome the limited amounts of training data, we demonstrate that 'synthetic agents' (Alife-style agents) can be used to develop flexible prior models of the person-to-person interactions.

[1] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[2] Matthew Brand,et al. Coupled hidden Markov models for modeling interacting processes , 1997 .

[3] Geoffrey E. Hinton,et al. Mean field networks that learn to discriminate temporally distorted strings , 1991 .

[4] Alex Pentland,et al. Real-time self-calibrating stereo person tracking using 3-D shape estimation from blob features , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5] Michael I. Jordan,et al. Probabilistic Independence Networks for Hidden Markov Probability Models , 1997, Neural Computation.

[6] Alex Pentland,et al. Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7] Michael I. Jordan,et al. Boltzmann Chains and Hidden Markov Models , 1994, NIPS.