点击次数：

论文类型：期刊论文

发表时间：2014-11-01

发表刊物：IEEE TRANSACTIONS ON CYBERNETICS

收录刊物：SCIE、EI、Scopus

卷号：44

期号：11,SI

页面范围：2099-2108

ISSN号：2168-2267

关键字：Color-based boosting algorithm; human body segmentation; top-down information

摘要：Human body segmentation is a challenging and important problem in computer vision. Existing methods usually entail a time-consuming training phase for prior knowledge learning with complex shape matching for body segmentation. In this paper, we propose a data-driven method that integrates top-down body pose information and bottom-up low-level visual cues for segmenting humans in static images within the graph cut framework. The key idea of our approach is first to exploit human kinematics to search for body part candidates via dynamic programming for high-level evidence. Then, by using the body parts classifiers, obtaining bottom-up cues of human body distribution for low-level evidence. All the evidence collected from top-down and bottom-up procedures are integrated in a graph cut framework for human body segmentation. Qualitative and quantitative experiment results demonstrate the merits of the proposed method in segmenting human bodies with arbitrary poses from cluttered backgrounds.