Streaming video object segmentation with the adaptive coherence factor

In this paper, we present a motion-adaptive algorithm for streaming object segmentation in monocular video sequences. To segment each frame, we fuse the cues from color, spatiotemporal contrast, and the bilayer labels on the previous frame in a two-frame graph. In the graph the coherence factor, the weight of the temporal smoothing term, is online estimated by the current frame, the previous frames and their segmentation results. The algorithm builds upon the observation that the amount of the object movement is approximately linear related to the summation of the temporal contrasts between adjacent frames. With the adaptive coherence factor we can improve the temporal coherence of the results when the object movement is changed. Finally each frame is segmented by binary graph cut. Experimental results show the effects of the adaptive coherence factor and validate the effectiveness of our proposed algorithm.