An Efficient Video Object Segmentation Algorithm Based on Change Detection And Background Updating

Abstract

In this paper, we propose a video object segmentation algorithm based on change detection and background updating that can quickly obtain video object from video sequence. The change detection is used to analyze temporal information between successive frames more efficiently than motion estimation. The combination both frame difference mask and background subtraction mask which is used to acquire the initial object mask and solve the uncovered background problem and still object problem. Moreover, the proposed boundary refinement is introduced to overcome the shadow influence and residual background problem. Finally, subjective and objective evaluations of the algorithm are demonstrated and the experimental results show that the spatial accuracy can be achieved above 95%.