An HMM-based segmentation method for traffic monitoring movies
Jien Kato, Takashi Watanabe, S. Joga, Jens Rittscher, Andrew Blake · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2002
Shadows of moving objects often obstruct robust visual tracking. We propose an HMM-based segmentation method which classifies in real time each pixel or region into three categories: shadows, foreground, and background objects. In the case of traffic monitoring movies, the effectiveness of the proposed method has been proven through experimental results.