Motion Detection using Wavelet-enhanced Accumulative Frame Differencing

Detecting and tracking moving objects in complicated real world scenes is a fundamental component for a wide variety of applications, including intelligent surveillance, advanced robotics, and human computer interaction. Based on this fundamental step, the subsequent processing is shaped up. Many standard algorithms are known for detecting moving objects, with different performances and time complexities, including optical flow, background subtraction, frame difference and wavelet filters. Existing frame differencing has a limited capability in detecting slowly moving objects, especially in the presence of illumination variations. In this paper, an innovative technique is proposed for the detection of moving objects in scenes with non-uniform illumination. The proposed technique is based on the idea of accumulative frame differencing and is enhanced using 2-D Discrete Wavelet Transform (DWT). Evaluation and comparison of the proposed technique with the different existing ones demonstrate the efficiency of using the 2-D DWT in the process of motion detection.