Extraction of the characteristic points for motion detection by using color information

The aim of this research is to extract the characteristic points for real-time automatic tracking of human figure. We propose the method of extracting the characteristic points to represent the human figure. The characteristic points are the points that indicate the position of human in each frame and can be employed to track the human motion. The variance of color image data around every pixels of the human figure is calculated and the pixels of more than threshold variance value are extracted for the candidates of the characteristic points. The points are distributed throughout the human figure by making certain area around the determined characteristic points forbidden area for characteristic points. Each characteristic point is extended to be square block for calculating matching correlation with the various position of the human figure in the frames followed. It is difficult to track human motion by considering and tracking all pixels of human figure, because it causes the very complex computation and consumes considerable processing time. The employing of the characteristic points made the matching correlation to be easier and faster than the employing all pixels of the human figure.