基于Haar型LBP纹理特征的人体姿态估计  

Human Pose Estimation Based on Haar Characteristics LBP Texture Feature

作　　者：袁紫华 李峰[1] 周书仁[1] 

机构地区：[1]长沙理工大学计算机与通信工程学院,长沙410004

出　　处：《计算机工程》2015年第4期199-204,共6页Computer Engineering

基　　金：湖南省自然科学基金资助项目(12JJ6057);湖南省教育厅科研基金资助项目(13B132);湖南省大学生研究性学习和创新性实验计划基金资助项目(湘教通[2012]402号136)

摘　　要：基于人体部件的树形模型表达直观且计算高效,被广泛应用在人体姿态估计中。然而模型本身在部件特征表达上的不足限制了姿态估计结果的准确度,为此,提出一种基于图结构模型和新型纹理特征的人体姿态估计算法。采用改进后的外观模型,从训练集中获得部件位置的先验知识,联系相邻部件之间的关系,并将其应用于测试图像的外观模型建模阶段。应用Haar型局部二值模式(HLBP)纹理特征,提取部件的纹理信息,对图像进行分块处理,并为每一块赋予不同的权重。实验结果表明,带权重的HLBP特征能更有效地提取部件的纹理特征,与HLBP特征、归一化HLBP特征和颜色特征相比能获得更高的准确度。Tree structured model based on body parts is widely used in human pose estimation filed due to its intuitive expression and effective calculation. In order to address the problem of low accuracy of pose estimation caused by insufficient feature expression of body part models,a pose estimation method based on pictorial structure and novel text feature is proposed. Better appearance model is adopted,prior and latent relationships of different body parts are learned from annotated images then help in estimating better appearance models on test images. Haar characteristics Local Binary Pattern（ HLBP） text feature is used to extract the text information of body parts. Furthermore,an image is block processed and different w eight is assigned to different block. Experimental results show that w hen compared w ith HLBP,normed HLBP and color feature,Weighted HLBP（ WHLBP） captures text feature more effectively and gains higher accuracy.

关 键 词：计算机视觉 人体姿态估计 外观模型 特征提取 纹理特征 加权Haar型局部二值模式特征 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]