Real-Time Motion Detection based on Discrete Cosine Transform

Abstract

We present motion detection algorithm by change detection filter matrix derived from Discrete Cosine Transform. Recently, a Fourier reconstruction scheme shows good results for motion detection. However, its computational cost is the major drawback. We revisit the problem and achieve two orders of magnitude faster than the previous algorithm with better performance. The proposed algorithm runs at about 800 frames per second for VGA resolution images on a consumer hardware by using only integer matrix multiplication and the symmetric property of change detection filter matrix. In addition, our algorithm is fundamentally robust to sudden illumination change because it works based on edge information. We verify our algorithm with challenging datasets that contain strong and sudden illumination changes.