Moving Object Detection for a Moving Camera Based on Global Motion Compensation and Adaptive Background Model

Abstract

A fast and effective moving object detection method for a moving camera is proposed in this paper. The global motion is estimated through tracking the grid-based key points using optical flow. After the motion compensation, the background model, candidate background model and candidate age are used for the background modelling. Then the local pixel difference and the consistency of local changes between the current frame and the background model are used for the background subtraction. The lighting influence threshold and the local pixel difference between the current frame and two previous aligned frames are used to reduce the lighting influences. Finally, Gaussian filter, connected-components analysis, erosion and dilation are used to refine the results. The performance evaluation shows that this proposed method works very fast in real time and has competitive results compared with others in the public dataset.