基于区域合并与轮廓模型的图像序列人物轮廓分割

doi:10.6040/j.issn.1672-3961.2.2013.333

山东大学学报(工学版) ›› 2014, Vol. 44 ›› Issue (6): 8-14.doi: 10.6040/j.issn.1672-3961.2.2013.333

基于区域合并与轮廓模型的图像序列人物轮廓分割

朱洪锦^1,2, 范洪辉^1,2, 叶飞跃^1,2, 臧海娟¹

1. 江苏理工学院计算机工程学院, 江苏常州 213001;
2. 云计算与智能信息处理常州市重点实验室, 江苏常州 213001

收稿日期:2013-06-28 修回日期:2014-03-17 出版日期:2014-12-20 发布日期:2013-06-28
作者简介:朱洪锦(1981-),女,吉林柳河人,讲师,博士,主要研究方向为模式识别与机器视觉.E-mail:zhuhongjin@jsut.edu.cn
基金资助:
国家自然科学基金资助项目(61302124);江苏省自然科学基金资助项目(BK20130235);江苏省高校自然科学基金资助项目(13KJB520006, 12KJD510005);江苏省“六大人才高峰”资助项目(DZXX-031);常州市应用基础研究资助项目(CJ20140049)

Human contour segmentation in image sequence based on region consolidation and contour model

ZHU Hongjin^1,2, FAN Honghui^1,2, YE Feiyue^1,2, ZANG Haijuan¹

1. College of Computer Engineering, Jiangsu University of Technology, Changzhou 213001, Jiangsu, China;
2. Key Laboratory of Cloud Computing & Intelligent Information Processing of Changzhou City, Changzhou 213001, Jiangsu, China

Received:2013-06-28 Revised:2014-03-17 Online:2014-12-20 Published:2013-06-28

摘要/Abstract

摘要： 为解决受图像背景复杂度影响,分水岭算法较难高精度实现图像序列中人物轮廓的分割与追踪这一问题,提出了利用颜色空间转换的区域合并实现目标轮廓区域的划分、并基于人物头部轮廓信息生成人物领域轮廓模型的方法。通过对人物领域边界线生成的初步轮廓模型进行高斯函数的卷积运算,生成形态轮廓模型的有效对象模板,实现图像序列的人物领域中不依靠序列差分和移动向量亦能在图像序列中追踪移动对象。基于颜色空间转换的区域合并和轮廓模型算法,可满足视频背景变动并且背景复杂的情况下对图像序列中的人物轮廓进行有效分割。实验结果验证了本算法的有效性与鲁棒性,可有效而稳定实现图像序列中人物轮廓的分割。

关键词: 分水岭算法, 轮廓模型, 颜色空间转换, 人物轮廓分割, 区域合并, 图像序列

Abstract: Affected by complexity of image background, it was more difficult to achieve high-precision of human contour tracking in image sequence based on watershed algorithm. In order to improve the detection precision, a region consolidation method based on color space transform and a contour model of head using head position information were proposed. The upper part of the human body template based on contour model of head and Gaussian function was founded. The proposed method could be achieved by human detection and tracking without motion vector and inter-frame difference. Human contour could be segmented correctly in image sequence based on color space transform of region consolidation and contour model of head in changing and complex video background. Experimental results demonstrated that human contour could be segmented effectively. The effectiveness and robustness of the proposed method were indicated by the experiments.

Key words: contour model, image sequence, color space transform, region consolidation, watershed algorithm, human contour segmentation

中图分类号:

TP391.4

朱洪锦, 范洪辉, 叶飞跃, 臧海娟. 基于区域合并与轮廓模型的图像序列人物轮廓分割[J]. 山东大学学报(工学版), 2014, 44(6): 8-14.

ZHU Hongjin, FAN Honghui, YE Feiyue, ZANG Haijuan. Human contour segmentation in image sequence based on region consolidation and contour model[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2014, 44(6): 8-14.

参考文献

[1] 罗嘉,韦志辉.基于几何活动轮廓模型的目标跟踪与快速运动估计[J]. 中国图像图形学报, 2009, 14(7):1361-1368. LUO Jia, WEI Zhihui. Tracking and fast motion estimation via geometric active contour model[J]. Journal of Image and Graphics, 2009, 14(7):1361-1368.
[2] WANG Z, XIAO N. Using MD-adaboost to enhance classifier of facial expression recognition[J]. Journal of Computational Information Systems, 2013, 9(3):923-932.
[3] 张萍,高立群,薛哈乐.一种新的几何活动轮廓模型在图像分割中的应用[J]. 东北大学学报:自然科学版, 2013, 34(5):632-636. ZHANG Ping, GAO Liqun, XUE Hale. A novel geometry active contour applied to image segmentation[J]. Journal of Northeastern University: Natural Science, 2013, 34(5):632-636.
[4] MAKOTO M, YONEYAMA M, SHIRAI K. Extraction of human face and transformable region by facial expression based on extended labeled graph matching[J]. Electronics and Communications in Japan, 2012, 87(10):35-43.
[5] WANG L, HE L, MISHRA A, et al. Active contours driven by local Gaussian distribution fitting energy[J]. Signal Processing, 2009, 89(12):2435-2447.
[6] 高颂,李富栋.图像边缘提取的区域联合分割与主动轮廓模型[J]. 激光与红外, 2013, 43(1):94-97. GAO Song, LI Fudong. Regional joint segmentation and active contour model of the image edge extraction[J]. Laser & Infrared, 2013, 43(1):94-97.
[7] MATTHEW B. Modeling regional dynamics of human—rangifer systems: a framework for comparative analysis[J]. Ecology and Society, 2013, 18(4):43.
[8] 潘改,高立群,赵爽.基于局部熵的主动轮廓模型[J].中国图象图形学报, 2013, 18(1):78-85. PAN Gai, GAO Liqun, ZHAO Shuang. Active contour model driven by local entropy energy[J]. Journal of Image and Graphics, 2013, 18(1):78-85.
[9] WU Y, YU T. A field model for human detection and tracking[J]. IEEE Trans PAMI, 2006, 28(5):753-765.
[10] GORELICK L, BLANK M, SHECHTMAN E, et al. Actions as space-time shapes[J]. IEEE Trans PAMI, 2007, 29(12):2247-2253.
[11] 孙晓云,王书朋,郑棋.参数轮廓模型的目标跟踪[J]. 西安科技大学学报, 2010, 30(1):123-126. SUN Xiaoyun, WANG Shupeng, ZHENG Qi. Object tracking based on parameterized contour model[J]. Journal of Xi'an University of Science and Technology, 2010, 30(1):123-126.
[12] 祝世平,郭智超,高洁,等. 基于Snake活动轮廓模型的视频跟踪分割方法[J]. 光电子激光, 2013, 24(1):139-145. ZHU Shiping, GUO Zhichao, GAO Jie, et al. A video object segmentation algorithm based on Snake models[J]. Journal of Optoelectronics Laser, 2013, 24(1):139-145.
[13] XING J, AI H, LAO S. Multiple human tracking based on multi-view upper-body detection and discriminative learning[C]//Proceedings of 20^th International conference on Pattern Recognition. Istanbul, Turkey:IEEECS Press, 2010:1698-1701.
[14] 乔磊, 李存华, 仲兆满,等. 基于规则的人物信息抽取算法的研究[J]. 南京师大学报: 自然科学版, 2012, 35(4):134-139. QIAO Lei, LI Cunhua, ZHONG Zhaoman, et al. Research on peoples information extraction based on rules[J]. Journal of Nanjing Normal University: Natural Science Edition, 2012, 35(4):134-139.
[15] WEI H, LANG B, ZUO Q. Contour detection model with multi-scale integration based on non-classical receptive field[J]. Neurocomputing, 2013, 103:247-262.
[16] XIE X, MIRMEHDI M. RAGS: region-aided geometric snake[J]. IEEE Transactions on Image Processing, 2004, 13(5):640-652.
[17] O'CALLAGHAN R, BULL D R. Combined morphological spectral unsupervised image segmentation[J]. IEEE Transactions on Image Processing, 2005, 14(1):49-62.
[18] CHEN T, TAN P, MA L, et al. PoseShop: human image database construction and personalized content synthesis[J]. IEEE Trans Vis Computer Graph, 2013, 19(5):824-837.
[19] 王新沛,刘常春,白瞳.基于均值距离的图像分割方法[J]. 山东大学学报:工学版, 2010, 40(4):36-41. WANG Xinpei, LIU Changchun, BAI Tong. An image segmentation method based on mean divergence[J]. Journal of Shandong University: Engineering Science, 2010, 40(4):36-41.
[20] COMANICIU D, RAMESH V, MEER P. Kernel-based object tracking[J]. IEEE Trans PAMI, 2003, 25(5):564-575.
[21] GAO H, SIU W, HOU C. Improved techniques for automatic image segmentation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11(12):1273-1280.
[22] 高丽,杨树元,李海强. 一种基于标记的分水岭图像分割新算法[J]. 中国图象图形学报, 2007, 12(6):1025-1032. GAO Li, YANG Shuyuan, LI Haiqiang. New unsupervised image segmentation via marker-based watershed[J]. Journal of Image and Graphics, 2007, 12(6):1025-1032.
[23] 孙亚新,战荫伟. 基于肤色模型与人脸特征的多姿态人脸检测[J]. 山东大学学报: 工学版, 2011, 41(2):36-40. SUN Yaxin, ZHAN Yinwei. Multi-pose face detection based on color model and face feature[J]. Journal of Shandong University: Engineering Science, 2011, 41(2):36-40.
[24] 朱洪锦,范洪辉,陈兴瑞,等. 基于局部自我相关函数光线照明变化下的人脸检测[J]. 山东大学学报:工学版, 2012, 42(5):59-64. ZHU Hongjin, FAN Honghui, CHEN Xingrui, et al. Image normalization based on local autocorrelation and its application to face detection[J]. Journal of Shandong University: Engineering Science, 2012, 42(5):59-64.
[25] WU B, NEVATIA R. Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors[J]. International Journal Computer Vision, 2007, 75(2):247-266.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于区域合并与轮廓模型的图像序列人物轮廓分割

Human contour segmentation in image sequence based on region consolidation and contour model

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

多维度评价

本文评价

推荐阅读 0

[1]	曲怀敬1,孙丰荣2,张运楚1,姚桂华3,吴延荣1,杨明强2. 一种IVUS序列图像内外膜边缘的自动提取方法[J]. 山东大学学报(工学版), 2011, 41(2): 5-11.
[2]	李前娜,孙丰荣,李艳玲,李晓峰,姚桂华,张运, . 基于时/空滤波噪声抑制算法和活动轮廓模型的血管内超声图像边缘提取[J]. 山东大学学报(工学版), 2006, 36(5): 44-48 .