电子科技大学学报2017，Vol.46Issue(2)：363-368,406,7.DOI:10.3969/j.issn.1001-0548.2017.02.008
矩阵的低秩稀疏表达在视频目标分割中的研究
Video Object Segmentation Via Low-Rank Sparse Representation
摘要
Abstract
We present a novel on-line algorithm for target segmentation and tracking in video. Superpixels, which are abstracted in every frame, are treated as data points in this paper. The object in current frame is represented as sparse linear combination of dictionary templates, which are generated based on the segmentation result in the previous frame. Then the algorithm capitalizes on the inherent low-rank structure of representation that are learned jointly. A low-rank sparse matrix optimal solution results in the construction of the trimap. At last, a simple energy minimization solution is adopted in segmented stage, leading to a binary pixel-wise segmentation. Experiments demonstrate that our approach is effective.关键词
能量最小/图分割/低秩/稀疏/视频目标分割Key words
energy minimization/graph cut/low rank/sparse/video object segmentation分类
信息技术与安全科学引用本文复制引用
顾菘,马争,解梅..矩阵的低秩稀疏表达在视频目标分割中的研究[J].电子科技大学学报,2017,46(2):363-368,406,7.基金项目
国家自然科学基金(61271288) （61271288）
教育部博士点基金(20130185130001) （20130185130001）
