摘要：The authors proposed a people recognition method for moving people of entering and leaving a video surveillance area employing the spatial-based feature of single-pedestrian image in conjunction with color vector. The spatial-based features are employed for its different location from variant parts of the human body. A histogram-based framework is used to describe the color vector of variant parts of the moving people. This method is able to track and identify the moving people successfully in different outdoor environment based on variance of samples. A series of experimental results illustrate that this method can track and identify automatically while the moving people enter or leave a video surveillance area.
关键词：computer vision; video segmentation; color-vector; object tracking; people recognition
