[1]肖锋,周杰.基于区域分割和蒙特卡洛采样的静态图片人体姿态估计[J].智能系统学报,2011,6(1):38-43.
XIAO Feng,ZHOU Jie.Human pose estimation in static images based on region segmentation and Monte Carlo sampling[J].CAAI Transactions on Intelligent Systems,2011,6(1):38-43.
点击复制
XIAO Feng,ZHOU Jie.Human pose estimation in static images based on region segmentation and Monte Carlo sampling[J].CAAI Transactions on Intelligent Systems,2011,6(1):38-43.
基于区域分割和蒙特卡洛采样的静态图片人体姿态估计
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
6
期数:
2011年第1期
页码:
38-43
栏目:
学术论文—机器感知与模式识别
出版日期:
2011-02-25
- Title:
- Human pose estimation in static images based on region segmentation and Monte Carlo sampling
- 文章编号:
- 1673-4785(2011)01-0038-06
- Keywords:
- static images; human pose estimation; region segmentation; Monte Carlo sampling; belief propagation
- 分类号:
- TP391.4
- 文献标志码:
- A
- 摘要:
- 静态图片中的人体姿态估计是近年来图像分析领域的重要问题之一.由于静态图片中可利用的信息较少，且存在多关节引起的形状畸变、着装变化、背景干扰及遮挡等难点，使得这一问题具有很大挑战性.考虑到现有算法的不足，提出了一种基于区域分割和置信传播蒙特卡洛采样的人体姿态估计算法，将前景区域分割加入到姿态估计中，在概率图模型中引入非树状的约束，采用蒙特卡洛采样来进行概率推理.实验表明该算法比经典的算法在公共数据集上给出了更加精确的估计结果，同时运行时间也减少了25%.
- Abstract:
- Human pose estimation in static images is one of the important issues in the field of image analysis in recent years. The main difficulties are that there’s less available information in static image, besides, there’re figure distortion due to multiple joints, change in clothes, background disturbance and shading, etc., which make the problem challenging. Aiming at the deficiency of existing algorithm, a new algorithm was proposed for human pose estimation in static images based on region segmentation, belief propagation and MonteCarlo sampling, in which foreground region segmentation was incorporated into the pose estimation, nontree constraints were introduced in the probabilistic graphical model, and MonteCarlo sampling was utilized to carry out probabilistic inference. Experimental results demonstrate that the proposed algorithm performs better on a common database compared with classical algorithm, producing a more precise estimate result and reducing 25% running time.
- 参考文献/References:
-
［1］EICHNER M, FERRARI V. Better appearance models for pictorial structures［C］//Proceedings of British Machine Vision Conference. London, UK， 2009: 617
［2］杨金锋，付周宇，谭铁牛，等.一种新型的基于内容的图像识别与过滤方法［J］.通信学报, 2004, 25(7): 93106.
YANG Jinfeng, FU Zhouyu, TAN Tieniu, et al. A novel algorithm for contentbased image recognition and filtering［J］. Journal of China Institute of Communications, 2004, 25(7): 93106.
［3］HU Weiming, WU Ou, CHEN Zhouyao, et al. Recognition of pornographic web pages by classifying texts and images ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 10191034.
［4］FELZENSZWALB P, HUTTENLOCHER D. Pictorial structures for object recognition ［J］. International Journal of Computer Vision, 2005, 61(1): 5579.
［5］MORI G, REN Xiaofeng, EFROS A, et al. Recovering human body configurations: combining segmentation and recognition［C］//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC, USA, 2004: 326333.
［6］REN Xiaofeng, BERG A, MALIK J. Recovering human body configurations using pairwise constraints between parts［C］//IEEE International Conference on Computer Vision. Beijing, China, 2005: 824831.
［7］ROBERTS T, MCKENNA S, RICKETTS I. Human pose estimation using partial configurations and probabilistic regions［J］. International Journal of Computer Vision, 2007, 73(3): 285306.
［8］LEE M, COHEN I. A modelbased approach for estimating human 3D poses in static images［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(6): 905916.
［9］HUA Gang, YANG Minghsuan, WU Ying. Learning to estimate human pose with data driven belief propagation［C］//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005: 747754.
［10］HU Zhilan, WANG Guijin, LIN Xinggang, et al. Recovery of upper body poses in static images based on joints detection［J］. Pattern Recognition Letters, 2009, 30(5): 503512.
［11］FERRARI V, MARINJIMENEZ M, ZISSERMAN A. Progressive search space reduction for human pose estimation［C］//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Anchorage, USA, 2008: 18.
［12］ZHANG Xiaoqin, LI Changcheng, TONG Xiaofeng, et al. Efficient human pose estimation via parsing a tree structure based human model［C］//IEEE International Conference on Computer Vision. Kyoto, Japan, 2009: 13491356.
［13］BERGTHOLDT M, JAPPES J, SCHMIDT S, et al. A study of partsbased object class detection using complete graphs［J］. International Journal of Computer Vision, 2010, 87(1/2): 93117.
［14］CHEN Qiang, ZHENG Enliang, LIU Yuncai. Pose estimation based on human detection and segmentation［J］. Science in China Series F: Information Sciences, 2009, 52(2): 244251.
［15］BOURDEV L, MALIK J. Poselets: body part detectors trained using 3D human pose annotation［C］//IEEE International Conference on Computer Vision. Kyoto, Japan, 2009: 13651374.
［16］RAMANAN D. Learning to parse images of articulated bodies［C］//Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems. Vancouver, Canada, 2006: 11291136.
［17］JONES M, REHG J. Statistical color models with application to skin detection［J］. International Journal of Computer Vision, 2002, 46(1): 8196.
［18］YEDIDIA J, FREEMAN W, WEISS Y. Understanding belief propagation and its generalizations［J］. Exploring Artificial Intelligence in the New Millennium, 2002, 8(1): 236239.
备注/Memo
收稿日期：2010-11-05.
基金项目：国家自然科学基金资助项目(60573062,60673106).
通信作者：肖锋.
E-mail:xiaof99@mails.tsinghua.edu.cn.
作者简介：
肖锋,男,1982年生,博士研究生,主要研究方向为姿态估计、图像处理、图片分类.
周杰,男,1968年生，教授、博士生导师，主要研究方向为模式识别、计算机视觉、多媒体信息处理、信息服务科学与技术.承担或完成国家自然科学基金、“863”计划项目等10余项，中国航海学会科学技术奖二等奖等多项奖励，在国外重要学术期刊上发表学术论文20余篇.
更新日期/Last Update:
2011-04-13