Real-time tracking of human body based on discrete wavelet transform

A novel colour-image real-time tracking system based on discrete wavelet transform is proposed in this paper for identifying human targets based on their color and spatial information. The configuration of the proposed tracking system includes a CCD camera mounted on a rotary platform for tracking moving objects. By using the position information of objects in the image frame captured by the camera, the rotary platform is controlled to position the tracking object around the central area of images to improve tracking efficiency. Existing researches of human-body tracking based on greyscale images generally ignored the facts that colours of the clothes that humans wear are salient features for identification purpose. As a result, we will incorporate colour information to establish important features for identifying human body in the proposed approach. Thanks to the use of discrete wavelet transform, computations, which are critical in real-time tracking, can be significantly reduced to achieve real-time tracking.