Please wait a minute...
浙江大学学报(工学版)
计算机技术﹑电信技术     
基于改进DRLSE的运动目标分割方法
胡祝华, 赵瑶池, 程杰仁, 彭金莲
海南大学 信息科学技术学院,海南 海口 570228
Moving object segmentation method based on improved DRLSE
HU Zhu-hua, ZHAO Yao-chi, CHENG Jie-ren, PENG Jin-lian
College of Information Science & Technology, Hainan University, Haikou 570228, China
 全文: PDF(2057 KB)   HTML
摘要:

为了得到精准、连续的运动目标轮廓,提出将帧间差分法和改进的距离规则水平集演化(DRLSE)方法结合应用于运动目标分割.采用帧间差分法得到运动目标的初始轮廓;使用在能量泛函的外力项中融入运动序列时空变化信息的DRLSE方法进行轮廓演化,避免演化受背景边缘干扰,得到精准的运动目标轮廓;根据精准目标轮廓的反馈估计运动方向,并结合帧间差分法为后续的DRLSE提供一个较佳的初始轮廓,能显著提高运动目标的分割速度.实验结果表明,与现有算法相比该改进方法能够更精确、更快地得到运动目标轮廓.

Abstract:

In order to get an accurate and continuous contour of moving target, a novel method to segment moving object by combining frame difference and an improved (DRLSE) is proposed. Firstly, the initial contour of moving target was obtained using frame difference. Secondly, the contour was evoluted with an improved DRLSE method, in which the spatial-temporal variable information in video sequences was merged into the external force field of energy functional to avoid the interference from background edge. Finally, the moving direction was estimated according to the feedback of the obtained accurate target contour, and by combining frame difference a better initial contour could be provided for the subsequent DRLSE, and thus the segmentation speed of moving object could be significantly improved. The experimental results show that the contour of moving target can be obtained more precisely and rapidly with the improved method introduced in this paper than with the existing methods.

出版日期: 2014-08-01
:  TP 391.41  
基金资助:

国家自然科学基金资助项目(61261024,61363071);海南省自然科学基金资助项目(614221);海南省教育厅基金资助项目(Hjkj2013-14);海南大学青年基金资助项目(qnjj1185、qnjj1245).

通讯作者: 赵瑶池,女,讲师     E-mail: yaochizi@163.com
作者简介: 胡祝华(1979—),男,讲师,博士生,从事信号处理、计算机视觉的研究.Email: eagler_hu@hainu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

胡祝华, 赵瑶池, 程杰仁, 彭金莲. 基于改进DRLSE的运动目标分割方法[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2014.08.019.

HU Zhu-hua, ZHAO Yao-chi, CHENG Jie-ren, PENG Jin-lian. Moving object segmentation method based on improved DRLSE. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2014.08.019.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2014.08.019        http://www.zjujournals.com/eng/CN/Y2014/V48/I8/1488

[1] KASS M, WITKIN A, TERZOPOULOS D. Snakes: active contour models [C]∥Proceedings-First International Conference on Computer Vision. London: IEEE, 1987: 259268.
[2] 钱芸, 张英杰.水平集的图像分割方法综述[J].中国图象图形学报,2008, 13(1): 713.
QIAN Yun, ZHANG Ying-jie. Level set methods and its application on image segmentation [J]. Journal of Image and Graphics, 2008,13(1): 713.
[3] 孔丁科.几何活动轮廓图像分割模型的研究[D].杭州:浙江大学, 2010: 311.
KONG Ding-ke. Research on geometric active contour models for image segmentation [D]. Hangzhou: Zhejiang University, 2010: 311.
[4] LI Chun-ming, XU Chen-yang, GUI Chang-feng, et al. Level set evolution without re-initialization: a new variational formulation [C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. San Diego: IEEE, 2005: 430436.
[5] LI Chun-ming, XU Chen-yang, GUI Chang-feng, et al. Distance regularized level set evolution and its application to image segmentation [J]. IEEE Transactions on Image Processing, 2010, 19(12): 32433254.
[6] 方宇强,戴斌,宋金泽,等.一种改进的基于活动轮廓和光流的运动目标分割方法 [J]. 中南大学学报:自然科学版, 2011, 42(4): 10351042.
FANG Yu-qiang, DAI Bin, SONG Jin-ze, et al. An improved moving objects segmentation method based on optical flow technique and active contour model [J]. Journal of Central South University :Science and Technology, 2011, 42(4): 10351042.
[7] 徐杨, 吴成东, 赵莹. 基于DRLSE模型的运动目标跟踪[J]. 计算机辅助设计与图形学学, 2012, 24(3): 345350.
XU Yang, WU Cheng-dong, ZHAO Ying. Moving object tracking using DRLSE model [J]. Journal of Computer-Aided Design & Computer Graphics, 2012, 24(3): 345350.
[8] 于慧敏,尤育赛.基于水平集的多运动目标检测和分割[J].浙江大学学报:工学版,2007, 41(3): 412417.
YU Hui-min, YOU Yu-sai. Detecting and segmenting multiple moving objects using level set method [J]. Journal of Zhejiang University: Engineering Science, 2007, 41(3): 412417.
[9] 李静,王军政,梁少敏,等.基于改进水平集的多运动目标检测方法[J].北京理工大学学报, 2011, 31(5): 557561.
LI Jing, WANG Jun-zheng, LIANG Shao-min, et al. Method of detecting multiple moving object based on improved level set [J]. Transactions of Beijing Institute of Technology, 2011, 31(5): 557561.
[10] ZHANG Rong-guo, YANG Li, LIU Kun, et al. Moving objective detection and its contours extraction using level set method[C]∥2012 International Conference on Control Engineering and Communication Technology, ICCECT 2012. Shenyang: IEEE, 2012: 778-781.
[11] 赵骥,冯闯,邵富群,等.基于自适应帧差和水平集的运动目标检测和分割[J].信息与控制 2012, 41(2): 153158.
ZHAO Ji, FENG Chuang, SHAO Fu-qun, et al. Moving object detection and segmentation based on adaptive frame difference and level set [J]. Information and Control, 2012, 41(2): 153-158.
[12] 王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京:科学出版社, 2008: 88-97
[13] 陈波,赖剑煌.用于图像分割的活动轮廓模型综述[J].中国图象图形学报,2007, 12(1): 11-20.
CHEN Bo, LAI Jian-huang. Active contour models on image segmentation: a survey [J]. Journal of Image and Graphics, 2007, 12(1): 11-20.
[14] CASELLES V, KIMMEL R, SAPIRO G. Geodesic active contours [J]. International Journal of Computer Vision, 1997, 22(1): 61-79.
[15] PARAGIOS N, DERICHE R. Geodesic active contours and level sets for the detection and tracking of moving objects [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(3): 266-280.
[16] OSHER S, SETHIAN J A. Front propagating with curvature dependent speed: algorithms based on Hamilton-Jacobi formulations [J]. Journal of Computational Physics, 1988, 79(1): 1249.

[1] 唐有宝, 卜巍, 邬向前. 多层次MSER自然场景文本检测[J]. 浙江大学学报(工学版), 2016, 50(6): 1134-1140.
[2] 吴一全,殷骏,朱丽,袁永明. 基于蜂群优化或分解的二维Arimoto灰度熵阈值分割[J]. 浙江大学学报(工学版), 2015, 49(9): 1625-1633.
[3] 王媛媛, 郭延恩, 施国全, 韦俊霞, 夏顺仁. 基于声图像的海底地形边界提取算法[J]. 浙江大学学报(工学版), 2015, 49(2): 376-383.
[4] 杨玉婷, 史玉回, 夏顺仁. 基于讨论机制的头脑风暴优化算法[J]. J4, 2013, 47(10): 1705-1711.
[5] 朱晓恩, 郝欣, 夏顺仁. 基于Levy flight的特征选择算法[J]. J4, 2013, 47(4): 638-643.
[6] 周水琴, 应义斌, 商德胜. 基于形态学的香梨褐变核磁共振成像无损检测[J]. J4, 2012, 46(12): 2141-2145.
[7] 孙创日,甄帅,夏顺仁. 基于吸引区域的多模态脑磁共振图像仿射配准[J]. J4, 2012, 46(9): 1722-1728.
[8] 谢迪, 童若锋, 唐敏, 冯阳. 具有高区分度的视频火焰检测方法[J]. J4, 2012, 46(4): 698-704.
[9] 戴渊明, 韦巍, 林亦宁. 基于颜色纹理特征的均值漂移目标跟踪算法[J]. J4, 2012, 46(2): 212-217.
[10] 李启雷, 金文光, 耿卫东. 基于无线惯性传感器的人体动作捕获方法[J]. J4, 2012, 46(2): 280-285.
[11] 刘晨彬,潘颖,张海石,黄峰平,夏顺仁. 基于磁共振图像的脑瘤MGMT表达状况检测算法[J]. J4, 2012, 46(1): 170-176.
[12] 李响,严晓浪,蒋清晓. 曲面表面文字平面化的算法[J]. J4, 2012, 46(1): 130-135.
[13] 钱诚, 张三元. 适用于目标跟踪的加权增量子空间学习算法[J]. J4, 2011, 45(12): 2240-2246.
[14] 吕谷来, 李建平, 李锵, 俞利兴, 朱松明, 楼建忠, 袁祎琳. 基于机器视觉的砧木定位识别方法[J]. J4, 2011, 45(10): 1766-1770.
[15] 曹颖, 郝欣, 朱晓恩, 夏顺仁. 基于自动随机游走的乳腺肿块分割算法[J]. J4, 2011, 45(10): 1753-1760.