递推式视频前景分割方法

Abstract

This paper presents a kind of recursive video object segmentation method. Previous video cutout methods present three major limitations especially for complex video scene: firstly they lack the ability to deal with the inseparable color problem between foreground and background scenes, and the occlusion/disocclusion problem caused by large movement, new exposed regions or topology change are also difficult to be solved. Lastly, the consideration on how to build the color model for the following probability estimation, which plays a critical role in the final result, has always been ignored in most of existing methods. In our method, all above limitations are taken full consideration. A kind of motion prediction method based on local coherence is adopted to separate the inseparable color. Then a self-adaptive extended sampling method is used to repair the video discontinuity caused by occlusion/disocclusion problem, and also we built the color model by sampling all the pixels from selected regions in order to make it clean and representative. Lastly, the final segmentation result is generated by using 3D Graph Cut algorithm according to the spatio-temporal coherence of the video. The experimental results are presented to demonstrate the effectiveness of the proposed method at achieving high quality results, as well as the robustness of the proposed method against several challenging test inputs.