(A) disparity-based adaptive multi-homography method for moving target detection based on global motion compensation

Abstract

Moving target detection is an important technique in visual surveillance systems. If a camera is freely moving, it becomes more difficult to detect a moving target, especially in the environment of a wide-range background. To compensate for the global motion of a wide-range background, a disparity-based adaptive multi-homography method is proposed. The proposed method comprises four steps

feature point extraction, generation of adaptive multi-homography matrices using motion grouping, generation of background model and detection of background, and target detection. This proposed method applied the background subtraction technique through the global motion compensation after using ViBe background model on the background motion derived by the multi-homography matrices. The devised adaptive multi-homography matrices method can increases a moving target detection rate since it decreases the residual signals by obtained on global motion compensation procedure. Experiment results show that the proposed method can robustly detect moving targets in sequences taken by a freely moving camera.