Moving object detection and tracking in wavelet compressed video

In many surveillance systems the video is stored in wavelet compressed form. An algorithm for moving object and region detection in video that is compressed using a wavelet transform (WT) is developed. The algorithm estimates the WT of the background scene from the WTs of the past image frames of the video. The WT of the current image is compared with the WT of the background and the moving objects are determined from the difference. The algorithm does not perform inverse WT to obtain the actual pixels of the current image nor the estimated background. This leads to a computationally efficient method and a system compared to the existing motion estimation methods. In a second aspect, size and locations of moving objects and regions in video is estimated from the wavelet coefficients of the current image, which differ from the estimated background wavelet coefficients. This is possible because wavelet coefficients of an image carry both frequency and space information. In this way, we are able to track the detected objects in video. Another feature of the algorithm is that it can determine slowing objects in video. This is important in many practical applications including highway monitoring, queue control, etc.