Expandable Data-Driven Graphical Modeling of Human Actions Based on Salient Postures

This paper presents a graphical model for learning and recognizing human actions. Specifically, we propose to encode actions in a weighted directed graph, referred to as action graph, where nodes of the graph represent salient postures that are used to characterize the actions and are shared by all actions. The weight between two nodes measures the transitional probability between the two postures represented by the two nodes. An action is encoded as one or multiple paths in the action graph. The salient postures are modeled using Gaussian mixture models (GMMs). Both the salient postures and action graph are automatically learned from training samples through unsupervised clustering and expectation and maximization (EM) algorithm. The proposed action graph not only performs effective and robust recognition of actions, but it can also be expanded efficiently with new actions. An algorithm is also proposed for adding a new action to a trained action graph without compromising the existin...

• Type: Journal
• Year: 2008
• Where: TCSV
• Authors: Wanqing Li, Zhengyou Zhang, Zicheng Liu
• Keywords: Action Graph, Salient Postures, TCSV 2008, Weighted Directed Graph