Hybrid Models for Human Motion Recognition

Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the human motion model as a triangulated graph. Previous approaches learned models based just on positions and velocities of the body parts while ignoring their appearance. Moreover, a heuristic approach was commonly used to obtain translation invariance. In this paper we suggest an improved approach for learning such models and using them for human motion recognition. The suggested approach combines multiple cues, i.e., positions, velocities and appearance into both the learning and detection phases. Furthermore, we introduce global variables in the model, which can represent global properties such as translation, scale or view-point. The model is learned in an unsupervised manner from unlabelled data. We show that the suggested hybrid probabilistic model (which combines global variables, like translation, with l...

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Claudio Fanti, Lihi Zelnik-Manor, Pietro Perona
• Keywords: Computer Vision, CVPR 2005, Global Variables, Human Motion Model, Human Motion Recognition, Hybrid Probabilistic Model, Suggested Approach Combines