项目名称: 基于结构化低秩表示的运动目标分割研究
项目编号: No.61300162
项目类型: 青年科学基金项目
立项/批准年度: 2014
项目学科: 自动化技术、计算机技术
项目作者: 孙玉宝
作者单位: 南京信息工程大学
项目金额: 25万元
中文摘要: 有效的运动目标分割是实现视频智能分析的一个重要前提。由于视频场景的复杂性以及背景的动态变化、目标的非刚体形变等因素影响,如何实现高效的目标分割是一个难点问题。本项目旨在于建立视频数据的结构化低秩表示模型,并将其应用于运动目标分割问题,将背景和前景分离为视频数据的低秩与稀疏部分,充分挖掘背景的低秩先验与前景运动目标的时空连续性先验,实现运动目标的鲁棒分割。项目首先研究背景的鉴别性低秩表示字典学习与前景目标的3D图结构化稀疏建模方法,进而构建基于图结构化低秩稀疏分解的分割模型及其快速算法,最后建立该模型的增量递推式处理机制。本项目通过在线学习背景字典使其自适应于复杂背景的动态变化,应用3D图融合时空上下文信息准确定位运动目标,增量分割模型适用于在线处理以及长时段视频的处理,不仅对拓展现有的矩阵低秩分解方法具有重要的理论意义,且在视频分析、视频对象编码等领域具有广泛的应用前景。
中文关键词: 低秩;结构化化稀疏;字典学习;图/超图学习;交替方向乘子法
英文摘要: Effective motion object segmentation is the premise and basis of intelligent video analysis. Owning to the complexity of background, the dynamic variations and the non-rigid deformation of motion objects, how to effectively segment the video object is a difficult problem. This proposal aims to construct a new structured low rank representation model for video data, which is then applied to the video motion object segmentation problem. The model decomposes the background and foreground as the low rank and sparse part of the video matrix respectively. The low rank prior of background and the temporal-spatial continuity prior of foreground motion objects is fully used to segment the motion objects robustly. We first study the discriminative dictionary learning method for low rank representation of scene background and 3D graph structured sparse model for foreground motion objects. Then video object segmentation model is constructed based on the structured low rank and sparse matrix decomposition of video matrix. Optimization algorithm is also proposed to solve the model fast. Lastly, increment and recursive processing mechanism is also designed. This proposal adapts to the dynamic change of the background by learning the background low rank representation dictionary adaptively. 3D graph structured sparsity model is
英文关键词: low rank;structured sparsity;dictionary learning;graph/hypergraph learning;alternating direction method of multipliers