Enhanced Human Parsing with Multiple Feature Fusion and Augmented Pose Model

CASIA OpenIR > 智能感知与计算研究中心

	Enhanced Human Parsing with Multiple Feature Fusion and Augmented Pose Model
	Zhaoxiang Zhang; Jianliang Hao; Yunhong Wang; Yuhang Zhao
	2014-08-24
会议名称	International Conference on Pattern Recognition
会议录名称	ICPR 2014
会议日期	24-28 August 2014
会议地点	Stockholm, Sweden
摘要	We address the problem of human pose estimation, which is a very challenging problem due to view angle variance, noise and occlusions. In this paper, we propose a novel human parsing method which can estimate diverse human poses from real world images. We merge the parallel lines feature and uniform LBP feature, thereby the new feature contains both shape and texture information, which can be used by discriminative body part detectors. The standard tree model is augmented by using virtual nodes in order to describe the correlations between originally unconnected nodes, which enhances the robustness of the traditional kinematic tree model. We test our method in a sports image dataset, and the experimental results demonstrate the advantages of the merged feature as well as the augmented pose model in real applications.
关键词	Estimation Kinematics Image Edge Detection Heuristic Algorithms Feature Extraction Biological System Modeling Inference Algorithms
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13239
专题	智能感知与计算研究中心
通讯作者	Zhaoxiang Zhang
推荐引用方式 GB/T 7714	Zhaoxiang Zhang,Jianliang Hao,Yunhong Wang,et al. Enhanced Human Parsing with Multiple Feature Fusion and Augmented Pose Model[C],2014.