作者: Y. Raja , S.J. McKenna , Shaogang Gong
关键词:
摘要: Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models estimate probability densities colour for skin, clothing background. These detect, track segment people, faces hands. A technique dynamically updating the accommodate changes apparent due varying lighting conditions was used. Two applications are highlighted: (1) actor segmentation virtual studios, (2) focus attention face gesture recognition systems. system implemented on a 200 MHz PC tracks multiple objects real time.