基于时空注意模型的视频分割算法  

Video Segmentation Based on Spatial-temporal Attention Model

作　　者：郑河荣[1] 褚一平[2] 潘翔[1] 

机构地区：[1]浙江工业大学计算机学院,杭州310014 [2]杭州电子科技大学计算机学院,杭州310018

出　　处：《中国图象图形学报》2010年第5期729-735,共7页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60703001);浙江省科技厅重大项目(2009C11G2020027);浙江省教育厅项目(Y200805048)

摘　　要：针对已有视频分割算法对复杂动态背景下所出现的误分割问题,提出通过显著性映射构造时空注意特征,并采用分层条件随机场进行视频分割,提高分割准确率。算法首先根据视觉注意理论提取时域和空域特征,并建立加权混合模型。其次,采用该混合模型计算运动目标的显著性映射概率分布,有效地提取出运动目标区域。最后,在显著性映射概率分布基础上,采用高斯混合模型建立前景和背景的能量函数,构造分层条件随机场模型对这些特征能量函数进行分割建模,精确地提取出运动对象目标。实验结果表明,该算法即使对复杂动态背景下的视频也能够得到稳定的分割效果,有效地去除摄像机运动等所导致的误分割问题。To deal with the error segmentation problem of the existing video algorithms under complex and dynamic scenes, the proposed method extracts spatial-temporal attention features with salient maps, and adopts hieiarchical conditional random field for video segmentation. Firstly, the algorithm constructs a weighted combination model based on spatial-temporal features by using information theory. Then, it uses the defined model to compute probability distribution of salient maps, which can locate region of moving object effectively. Finally, the Gaussian mixture model is adopted to construct energy functions with the above probability distribution, and the hierarchical conditional random field is used to constraint these feature energy functions to refine final segmentation. The experiment results showed that the algorithm can avoid the error segmentation problem induced by camera movement. So it is robust to handle the videos under complex and dynamic scenes.

关 键 词：视频分割 时空信息注意模型 分层条件随机场 

分 类 号：TP391.6[自动化与计算机技术—计算机应用技术]