基于骨架匹配的人体轮廓线提取

doi:10.16182/j.issn1004731x.joss.201711025

系统仿真学报 ›› 2017, Vol. 29 ›› Issue (11): 2774-2781.doi: 10.16182/j.issn1004731x.joss.201711025

基于骨架匹配的人体轮廓线提取

张远^1,2,3, 蒋浩^1,2, 朱登明^1,2, 王兆其^1,2

1.中国科学院计算技术研究所,北京 100190;
2.移动计算与新型终端北京市重点实验室,北京 100190;
3.中国科学院大学,北京 100049

收稿日期:2016-05-10 发布日期:2020-06-05
作者简介:张远(1994-),男,山西忻州,硕士生,研究方向为计算机图形学;蒋浩(1982-),男,湖南株洲,博士,助理研究员,研究方向为群体行为模拟。
基金资助:
国家自然科学基金(61173067,61379085,61532002),国家863计划(2015AA016401)

Human Contour Extraction Based on Skeleton Matching

Zhang Yuan^1,2,3, Jiang Hao^1,2, Zhu Dengming^1,2, Wang Zhaoqi^1,2

1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China;
2. Beijing Key Laboratory of Mobile Computing and Pervasive Device, Beijing, 100190, China;
3. University of Chinese Academy of Sciences, Beijing, 100049, China

Received:2016-05-10 Published:2020-06-05

摘要/Abstract

摘要： 为了生成静态图像中人体的轮廓线,提出了一种基于骨架匹配的轮廓线提取方法。在图像中找到可以表征人体骨架的骨架关键点,通过骨架关键点,利用图像中各像素点所包含的边缘信息,结合人体形态学先验知识,构建了隐马尔科夫模型来匹配人体上对应骨架关键点的边缘关键点,少量的边缘关键点即可生成人体大致轮廓。利用Hermite插值方法连接边缘关键点获取人体轮廓线。通过相关实验结果表明,提出的方法在较为简单的场景中可以提取出静态图像中人体轮廓,获得的轮廓也符合人体形状先验。与已有的方法相比,在速度上有了很大的提高,并在一些较为复杂的场景中取得了更好的效果。

关键词: 轮廓提取, 隐马尔科夫模型, 人体形态学, Hermite插值

Abstract: To extract human contour in still images, we propose a human contour extraction method based on skeleton matching. Skeleton key points are points representing human skeleton in images. Optimal human contour key points corresponding to skeleton key pointscanbe extracted by constructing hidden Markov modelthrough skeleton key points and image pixels' edge information combined with human body morphology as prior knowledge. Few human contour key points can generate reasonable human contour. TheHermiteinterpolation is usedto connect these key points to obtain human contour. Experimentresults show thatour method can extract reasonable human contour in simple scene, andhas higher speed and achieves better results in complicated scenecompared to previous methods.

Key words: contour extraction, hidden Markov model, human body morphology, Hermiteinterpolation

中图分类号:

TP.391.9

张远, 蒋浩, 朱登明, 王兆其. 基于骨架匹配的人体轮廓线提取[J]. 系统仿真学报, 2017, 29(11): 2774-2781.

Zhang Yuan, Jiang Hao, Zhu Dengming, Wang Zhaoqi. Human Contour Extraction Based on Skeleton Matching[J]. Journal of System Simulation, 2017, 29(11): 2774-2781.

参考文献

[1] Ren X, Berg A C, Malik J.Recovering human body configurations using pairwise constraints between parts[C]. ICCV, 2005, 1:824-831.
[2] Mori G, Malik J.Estimating human body configurations using shape context matching[C]// European conference on computer vision, 2002, 150-180.
[3] 孙庆杰, 吴恩华.基于矩形拟合的人体检测[J]. 软件学报, 2003, 14(8): 1388-1393.
Sun Qing-Jie, Wu En-Hua.Human Detection Based on Rectangle Fitting[J]. Journal of Software, 2003, 14(8): 1388-1393.
[4] 吕治国, 徐昕,贺汉根.基于可变模板和支持向量机的人体检测[J]. 计算机应用, 2007, 27(9): 2258-2261.
LüZhi-guo, XuXin, He Han-gen. Human detection based on deformable template and SVM[J]. Computer Applications, 2007, 27(9): 2258-2261.
[5] Mohan A, Papageorgiou C, Poggio T.Example-based object detection in images by components[J]. IEEE transactions on pattern analysis and machine intelligence, 2001, 23(4): 349-361.
[6] Mori G, Ren X, Efros A A, et al.Recovering human body configurations: Combining segmentation and recognition[C]//Computer Vision and Pattern Recognition, 2004, 2: 326-333.
[7] Ferrari V, Marin-Jimenez M, Zisserman A.Progressive search space reduction for human pose estimation[C]// Computer Vision and Pattern Recognition, 2008: 1-8.
[8] Rother C, Kolmogorov V, Blake A.Grabcut: Interactive foreground extraction using iterated graph cuts[J]. ACM transactions on graphics (TOG), 2004, 23(3):309-314.
[9] Bray M, Kohli P, Torr P H.Posecut: Simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts[C]//European conference on computer vision, 2006: 642-655.
[10] 潘锋,王宣银.基于支持向量机的复杂背景下的人体检测[J].中国图象图形学报, 2005, 10(2): 181-186.
Pan Feng, Wang Xuan-yin.Support Vector Machine-Based Human Detection under Complex Backgroud[J]. Journal of Image and Graphics, 2005, 10(2): 181-186.
[11] Andriluka M., Roth S., &Schiele B.Pictorial structures revisited: People detection and articulated pose estimation[C]//Computer Vision and Pattern Recognition, 2009: 1014-1021.
[12] Yang Y, Ramanan D.Articulated human detection with flexible mixtures of parts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12): 2878-2890.
[13] Junior J C J, Jung C R, Musse S R. Skeleton-based human segmentation in still images[C]//Image Processing (ICIP), 2012: 141-144.
[14] 吴壮志, 廖爽爽, 聂磊, 等.基于图像的人体参数测量系统的设计与实现[J]. 湖南大学学报(自然科学版), 2010, 37(9): 88-92.
Wu Zhuang-zhi, Liao Shuang-shuang, NieLei, et al. Design and Implementation of Human Size Measurement System Based on Images[J]. Journal of Hunan University, 2010, 37(9): 88-92.
[15] 赵静秒, 李晓久, 王玉秀,等.基于阈值的人体数字图像测量点的确定[J]. 天津工业大学学报, 2004, 23(5): 98-101.
Zhao Jing-miao, Li Xiao-jiu, Wang Yu-xiu, et al.Confirmation of pivotal points for measurement of body digital images based threshold[J]. Journal of Tianjin Polytechnic University, 2004, 23(5): 98-101.
[16] Freifeld O, Weiss A, ZuffiS, et al. Contour people: A parameterized model of 2D articulated human shape[C]//Computer Vision and Pattern Recognition, 2010: 639-646.
[17] Guan P, Weiss A, Balan A O, et al.Estimating human shape and pose from a single image[C]// ICCV, 2009, 1381-1388.
[18] Jacques J C, Jung C R,Müsse S R.Head-shoulder human contour estimation in still images[C]//Image Processing (ICIP), 2014, 278-282.
[19] Jacques J C S,Musse S R.Improved head-shoulder human contour estimation through clusters of learned shape models[C]//Graphics, Patterns and Images (SIBGRAPI), 2015, 329-336.
[20] Xin H, Ai H, Chao H.et al.Human head-shoulder segmentation[C]//Automatic Face &Gesture Recognition and Workshops (FG 2011), 2011: 227-232.
[21] Tilley A R.The measure of man and woman: human factors in design[M]. John Wiley & Sons, 2002.

基于骨架匹配的人体轮廓线提取

Human Contour Extraction Based on Skeleton Matching

PDF (PC)

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 1

编辑推荐

Metrics

本文评价