Recognizing Activities with Multiple Cues

In this paper, we introduce a first-order probabilistic model that combines multiple cues to classify human activities from video data accurately and robustly. Our system works in a realistic office setting with background clutter, natural illumination, different people, and partial occlusion. The model we present is compact, requires only fifteen sentences of first-order logic grouped as a Dynamic Markov Logic Network (DMLNs) to implement the probabilistic model and leverages existing state-of-the-art work in pose detection and object recognition.

• Type: Conference
• Year: 2007
• Where: HUMO
• Authors: Rahul Biswas, Sebastian Thrun, Kikuo Fujimura
• Keywords: Computer Animation, Dynamic Markov Logic, HUMO 2007, Probabilistic Model, first-order Probabilistic Model