基于Haar 型LBP 纹理特征的人体姿态估计

doi:10.3969/j.issn.1000-3428.2015.04.038

计算机工程

基于Haar 型LBP 纹理特征的人体姿态估计

袁紫华,李　峰,周书仁

(长沙理工大学计算机与通信工程学院,长沙410004)

收稿日期:2014-04-28 出版日期:2015-04-15 发布日期:2015-04-15
作者简介:袁紫华(1989 - ),女,硕士研究生,主研方向:人体姿态估计,图像处理,模式识别;李　峰,教授、博士;周书仁,副教授、博士。
基金项目:
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)。

Human Pose Estimation Based on Haar Characteristics LBP Texture Feature

YUAN Zihua,LI Feng,ZHOU Shuren

(School of Computer and Communication Engineering,Changsha University of Science and Technology,Changsha 410004,China)

Received:2014-04-28 Online:2015-04-15 Published:2015-04-15

摘要/Abstract

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。

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

Abstract: 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 weight is assigned to different block. Experimental results show that when compared with HLBP,normed HLBP and color feature,Weighted HLBP(WHLBP) captures text feature more effectively and gains higher accuracy.

Key words: computer vision, human pose estimation, appearance model, feature extract, texture feature, Weighted Haar characteristics Local Binary Pattern(WHLBP)

中图分类号:

TP391

袁紫华,李峰,周书仁. 基于Haar 型LBP 纹理特征的人体姿态估计[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2015.04.038.

YUAN Zihua,LI Feng,ZHOU Shuren. Human Pose Estimation Based on Haar Characteristics LBP Texture Feature[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2015.04.038.

参考文献

参考文献 [ 1 ]　Felzenszwalb P F. Pictorial Structure for Object Recognition[ J]. International Journal of Computer Vision,2005, 61(1):55-79. [ 2 ]　Johnson S, Everingham M. Combining Discriminative Appearance and Segmentation Cues for Articulated Human Pose Estimation [ C ] / / Proceedings of International Conference on Computer Vision. Washington D. C. ,USA:IEEE Press,2010:396-407. [ 3 ]　Eichner M, Jimenez M M, Zisserman A, et al. 2D Articulated Human Pose Estimation and Retrieval in (Almost) Unconstrained Still Images [J]. International Journal of Computer Vision,2012,99(2):190-214. [ 4 ]　Andriluka M,Roth S,Schiele B. Pictorial Structures Revisited: People Detection and Articulated Pose Estimation[ C] / / Proceedings of Conference on Computer Vision and Pattern Recognition. Washington D. C. , USA:IEEE Press,2009:1014-1021. [ 5 ]　Lan Xiaoyang, Huttenlocher D P. Beyond Trees: Common-factor Models for 2D Human Pose Recovery[C] / / Proceedings of International Conference on Computer Vision. Washington D. C. , USA: IEEE Press,2005:470-477. [ 6 ]　Tian Taipeng, Sclaroff S. Fast Globally Optimal 2D Human Detection with Loopy Graph Model [ C ] / / Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C. , USA:IEEE Press,2010:81-88. [ 7 ]　周书仁,殷建平. 基于Haar 特性的LBP 纹理特征[J]. 软件学报,2013,24(8):1909-1926. [ 8 ]　Ramanan D. Learning to Parse Images of Articulated Bodies[C] / / Proceedings of the 20th Annual Conference on Neural Information Processing Systems. Vancouver, Canada:MIT Press,2006:1129-1136. [ 9 ]　Nocedal J,Wright S J. Numerical Optimization[M]. 2nd ed. New York,USA:Springer-Verlag,2006. [10]　Viola P,Jones M J. Rapid Object Detection Using a Boosted Cascade of Simple Features [C] / / Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D. C. , USA:IEEE Press,2001:511-518. [11]　Ojala T, Pietik?inen M, Harwood D. A Comparative Study of Texture Measures with Classification Based on Featured Distributions [ J ]. Pattern Recognition,1996, 29(1):51-59. [12]　Felzenszwalb P,McAllester D,Ramanan D. A Discriminatively Trained,Multiscale,Deformable Part Model[C]/ / Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C. ,USA:IEEE Press, 2008:1-8. [13]　Rother C,Kolmogorov V,Blake A. Grabcut:Interactive Foreground Extraction Using Iterated Graph Cuts [J]. ACM Transactions on Graphics,2004,23(3):309-314. 编辑　顾逸斐

[1]	王旭, 陈永乐, 王庆生, 陈俊杰. 结合特征选择与集成学习的密码体制识别方案[J]. 计算机工程, 2021, 47(1): 139-145,153.
[2]	张艺, 周雯, 梁意文, 谭成予. 基于数字微分的函数化树突状细胞算法模型[J]. 计算机工程, 2020, 46(9): 54-60.
[3]	张国令, 王晓丹, 李睿, 来杰, 向前. 基于栈式降噪稀疏自编码器的极限学习机[J]. 计算机工程, 2020, 46(9): 61-67.
[4]	生龙, 马建飞, 杨瑞欣, 吴迪. 基于特征交换的CNN图像分类算法研究[J]. 计算机工程, 2020, 46(9): 268-273.
[5]	谢瑞, 邵堃, 霍星, MITHUN Md Masud Parvej. 一种改进的DIQaM_FR/NR图像质量评价模型[J]. 计算机工程, 2020, 46(8): 258-263,270.
[6]	郑伟成, 李学伟, 刘宏哲, 代松银. 基于深度学习的疲劳驾驶检测算法[J]. 计算机工程, 2020, 46(7): 21-29.
[7]	罗彬珅, 刘利民, 董健, 刘璟麒. 基于SAE-GA-SVM模型的雷达新型干扰识别[J]. 计算机工程, 2020, 46(6): 281-287.
[8]	郑秋梅, 王璐璐, 王风华. 基于改进卷积神经网络的交通场景小目标检测[J]. 计算机工程, 2020, 46(6): 26-33.
[9]	沈泽君, 丁飞飞, 杨文元. 多粒度相关滤波视频跟踪方法[J]. 计算机工程, 2020, 46(5): 274-281.
[10]	曾娅琴, 张琳琳, 张若楠, 杨波. 基于MobileNet的恶意软件家族分类模型[J]. 计算机工程, 2020, 46(4): 162-168.
[11]	康雁, 杨其越, 李浩, 梁文韬, 李晋源, 崔国荣, 王沛尧. 基于主题相似性聚类的自适应文本分类[J]. 计算机工程, 2020, 46(3): 93-98.
[12]	衡红军, 刘静. 基于混合方法的多维时间序列驾驶异常点检测[J]. 计算机工程, 2020, 46(3): 99-104.
[13]	陈良臣, 高曙, 刘宝旭, 陶明峰. 网络流量异常检测中的维数约简研究[J]. 计算机工程, 2020, 46(2): 11-20.
[14]	齐永锋, 李陇强. 基于局部模式的癫痫脑电信号自动分类方法[J]. 计算机工程, 2020, 46(2): 298-303.
[15]	刘宜成, 廖鹭川, 张劲, 吴浩, 何凌, 戴弘宁, 张晗, 杨刚. 基于轨迹和形态识别的无人机检测方法[J]. 计算机工程, 2020, 46(12): 283-289,298.

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

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10