Toward real-time extraction of pedestrian contexts with stereo camera
Kei Suzuki, Kazunori Takashio, Hideyuki Tokuda, Masaki Wada, Yusuke Matsuki, Kazunori Umeda · 2008
We extract the mood of disquiet on street corners in real-time with stereo video camera systems. Last year we proposed a novel stereo measurement algorithm to detect moving people, which was focusing on moving region in video data. In this paper, we report our prototype of probabilistic inference engine that can detect contexts of individual pedestrian and groups of pedestrians. We demonstrated that the real-time extraction of higher-level pedestrian contexts using the Bayesian Network model was effective for extracting several pedestrians’ context.