Video object segmentation based on supervoxel for multimedia corpus construction

Multimedia corpus is efficient for second language acquisition when we tag texts, scripts or objects in language materials and retrieve the corresponding video or audio parts. This paper presents an automatic video object segmentation method based on supervoxel in a multimedia corpus. In this method, a novel algorithm is proposed for generating the supervoxel. In 3D video volume, motion consistence of moving object is a frequent challenge for segmentation algorithm and a robust, long-term supervoxel could help in this situation. The segmentation process is considered as a minimization of an energy function where variables are labels of supervoxels. The supervoxel-based energy function consists of two terms, which are data term and smoothness term. The data term estimates the likelihood of a supervoxel to be labeled as moving object or background according to an appearance model and a motion model. The appearance model is based on an automatic processing for color collection. The motion model is derived from acting center-surround filter on an optical flow field. The supervoxel-based appearance and geometry cues are used to build smoothness term. The final segmentation can be obtained by minimizing the energy function which is defined on a spatio-temporal 3D video volume. We present experimental results of our method which outperforms the state-of-the-art methods on standard test sequences.