Adaptive Stereo Video Object Segmentation Based on Depth and Spatio-temporal Information

In this paper, we present an adaptive stereo video object segmentation algorithm based on depth and spatio-temporal information. First, the object is extracted from the left channel with a new algorithm, which consists of three steps: depth segmentation, adaptive change detection based on twice frame-difference, and edge modification. Then, an inverse matching operation is proposed for object extraction from the right channel according to the extracted object in the left channel and disparity map. Finally experimental results demonstrate that our proposed algorithm successfully extracts moving objects from various stereo video sequences, even if the objects hold still or move slowly in several frames, and this algorithm can solve the problem of extracting multiple objects overlapped.