Multiresolution based sigma-delta for motion segmentation

Motion segmentation is an important research field as it forms the stepping stone for traffic monitoring, video surveillance, activity analysis, gait recognition and many other automatic imaging applications. In this work, a novel generic multiresolution (MR) based framework has been proposed in conjunction with Sigma-delta based motion segmentation algorithm. The framework provides a general platform to use any MR analysis method to 1) incorporate subbands information containing varying features for enhanced motion extraction and 2) combine the information obtained to incrementally form the background using Sigma-delta method and upscale to original frame resolution. The validity of the proposed method is demonstrated using four popular MR analysis methods. Comparison of the proposed framework with sigma-delta and wavelet based change detection reflects several improvements over these methods.