A Phase Discrepancy Analysis of Object Motion

Abstract. Detecting moving objects against dynamic backgrounds remains a challenge in computer vision and robotics. This paper presents a surprisingly simple algorithm to detect objects in such conditions. Based on theoretic analysis, we show that 1) the displacement of the foreground and the background can be represented by the phase change of Fourier spectra, and 2) the motion of background objects can be extracted by Phase Discrepancy in an efficient and robust way. The algorithm does not rely on prior training on particular features or categories of an image and can be implemented in 9 lines of MATLAB code. In addition to the algorithm, we provide a new database for moving object detection with 20 video clips, 11 subjects and 4785 bounding boxes to be used as a public benchmark for algorithm evaluation.

• Type: Journal
• Year: 2010
• Where: ACCV
• Authors: Bolei Zhou, Xiaodi Hou, Liqing Zhang
• Keywords: ACCV 2010, Algorithm, Algorithm Evaluation, Computer Vision, Simple Algorithm