A hierarchical Bayesian network for event recognition of human actions and interactions

Abstract

Recognizing human interactions is a challenging task due to the multiple body parts of interacting persons and the concomitant occlusions. This paper presents a method for the recognition of two-person interactions using a hierarchical Bayesian network (BN). The poses of simultaneously tracked body parts are estimated at the low level of the BN, and the overall body pose is estimated at the high level of the BN. The evolution of the poses of the multiple body parts are processed by a dynamic Bayesian network (DBN). The recognition of two-person interactions is expressed in terms of semantic verbal descriptions at multiple levels: individual body-part motions at low level, single-person actions at middle level, and two-person interactions at high level. Example sequences of interacting persons illustrate the success of the proposed framework. Surveillance - Event recognition - Human interaction - Motion - Bayesian network.