全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

融合多特征的运动一致性图像分割

DOI: 10.11834/jig.20140507

Keywords: 彩色图像分割,运动一致性,区域相似性度量,区域合并

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的在彩色图像分割中,光流法能够得到运动区域,但难以获得运动目标准确的分割边界,而常用的算法往往会产生过分割。为了克服光流法的不足,在保留显著性区域的同时抑制过分割,从而获得具有运动一致性区域的分割结果,提出融合多特征的运动一致性图像分割算法。方法首先通过MeanShift算法获取图像的初始分割,然后利用空域信息,包括颜色、边缘和区域面积等对视觉感知上具有相似性的区域进行合并,再利用时域信息进行运动一致性区域合并,最终得到分割结果。结果实验结果表明通过结合时空信息,该方法能够有效抑制过分割,不仅弥补了光流场不能准确提取目标边缘的不足,而且提高了分割目标的完整性。结论与两种流行的彩色图像分割算法相比,所提方法获得了更加理想的结果。

References

[1]  Lin K Y, Wu J H, Xu L H. A survey on color image segmentation techniques [J]. Journal of Image and Graphics, 2005,10(1):1-10. [林开颜, 吴军辉, 徐立鸿. 彩色图像分割方法综述 [J]. 中国图象图形学报, 2005, 10(1):1-10.][DOI:10.11834/jig.20050103]
[2]  Xu X Z, Ding S F, Shi Z Z, et al. New theories and methods of image segmentation [J]. Acta Electronica Sinica, 2010,38(2A):76-82. [许新征, 丁世飞, 史忠植, 等. 图像分割的新理论和新方法 [J]. 电子学报, 2010, 38(2A):76-82.]
[3]  Kuan Y H, Kuo C M, Yang N C. Color-based image salient region segmentation using novel region merging strategy [J]. IEEE Trans. on Multimedia, 2008, 10(5):832-845.
[4]  Ning J F, Zhang L, Zhang D, et al. Interactive image segmentation by maximal similarity based region merging [J]. Pattern Recognition, 2010, 43(2):445-456.
[5]  Zhou J X, Zhu J J, Zhao Q H. Images segmentation by integrating two approaches of improved Mean Shift and region merging [J]. Science of Surveying and Mapping, 2012,37(6):98-101. [周家香, 朱建军, 赵群河. 集成改进Mean Shift和区域合并两种算法的图像分割 [J]. 测绘科学, 2012, 37(6):98-101.]
[6]  Christoudias C M. Edge Detection and Image Segmentation (EDISON) System ver1.0 [EB/OL]. 2003-04-14[2013-08-10].www.caip.rutgers.edu/riul/
[7]  Zhu S C, Yuille A. Region competition: unifying snakes, region growing, and Bayes/MDI, for multiband image segmentation [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1996, 18(9):884-900.
[8]  Fan J, Yan D K Y, Elmagarmid A K, et al. Automatic image segmentation by integrating color-edge extraction and seeded region growing [J]. IEEE Trans. on image Processing, 2001, 10(10):1451-1466.
[9]  Li S Q, Xu J C, Ren J Y, et al. A color image segmentation algorithm by integrating watershed with region merging [J]. Lecture Notes in Computer Science, 2012, 7414(1): 167-173.
[10]  Yu W S, Hou Z Q, Song J J. Color image segmentation based on marked-watershed and region-merger [J]. Acta Electronica Sinica, 2011,39(5):1007-1012. [余旺盛, 侯志强, 宋建军. 基于标记分水岭和区域合并的彩色图像分割 [J]. 电子学报, 2011, 39(5):1007-1012.]
[11]  Bouthemy P, Francois E. Motion segmentation and qualitative dynamic scene analysis from an image sequence [J]. IJCV, 1993, 10(2):157-182.
[12]  Khan S, Shah M. Object based segmentation of video using color, motion and spatial information [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattrn Recognition. Colorado Springs: IEEE, 2011, 2: 746-751.
[13]  Hong Z H, Wang Z H, Zhou R J. An method for video object segmentation based on motion homogenization [J]. Journal of Naval University of Engineering, 2007, 19(4):90-94. [洪泽宏, 王占辉, 周榕军. 基于运动一致性的视频对象分割方法研究 [J]. 海军工程大学学报, 2007, 19(4):90-94.]
[14]  Zhang X B, Liu W Y, Lv D W. Automatic video object segmentation algorithm based on spatio-temporal information [J]. Journal of Optoelectronics?Laser, 2008, 19(3):384-387. [张晓波, 刘文耀, 吕大伟. 基于时空信息的自动视频对象分割算法 [J]. 光电子?激光, 2008, 19(3):384-387.]
[15]  Liu Z, Yang J, Peng N S. Video object segmentation based on hypothesis testing and region merging [J]. Journal of Data Acquisition & Processing, 2004,19(2):124-129. [刘志, 杨杰, 彭宁嵩. 基于假设检验和区域合并的视频对象分割 [J]. 数据采集与处理, 2004, 19(2):124-129.]
[16]  Li G, Wang Z Y, Hou Z Q. Color image segmentation algorithm based on k-means clustering and region merging [J]. Journal of Computer Applications, 2010, 30(2):354-358. [李光, 王朝英, 侯志强. 基于K均值聚类与区域合并的彩色图像分割算法 [J]. 计算机应用, 2010, 30(2):354-358.]
[17]  Liu H, Zhang Y S, Zhang Y H, et al. Vector morphology image processing based on differrence formula in uniform space [J]. Journal of Image and Graphics, 2011, 16(12):2145-2151.[刘辉, 张云生, 张印辉, 等.均匀空间色差度量的矢量形态学图像处理[J].中国图象图形学报, 2011, 16(12):2145-2151.]
[18]  Chen L X, Chen Z J. Image retrieval algorithms based on lab space [J]. Computer Engineering, 2008,34(13):224-226. [陈丽雪, 陈昭炯. 基于Lab空间的图像检索算法 [J]. 计算机工程, 2008, 34(13):224-226.]
[19]  Zhang S M. The method of color image segmentation based on color clustering and region growing [D]. Chengdu: Chengdu University of Technology, 2008. [章三妹. 基于聚类和区域生长的彩色图像分割方法 [D]. 成都: 成都理工大学, 2008.]
[20]  Ye Q X, Gao W, Wang W Q, et al. A color image segmentation algorithm by using color and spatial information [J]. Journal of Software, 2004,15(4): 522-530. [叶齐祥, 高文, 王伟强, 等. 一种融合颜色和空间信息的彩色图像分割算法 [J]. 软件学报, 2004, 15(4): 522-530.]
[21]  更多...
[22]  Zhang J H. Digital watermarking techniques based on image segmentation and svd [J]. Journal of Wuhan University of Technology, 2010,32(2):146-150. [张金辉. 基于图像分割和SVD的数字水印算法 [J]. 武汉理工大学学报, 2010, 32(2):146-150.]
[23]  Brox T, Malik J. Large displacement optical flow: descriptor matching in variational motion estimation [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2011, 33(3):500-513.
[24]  Liu C. Beyond pixels: exploring new representations and applications for motion analysis [D]. Cambridge: Massachusetts Institute of Technology, 2009.
[25]  Liu C. Optical Flow Matlab/C++ Code [EB/OL].2011-08-01[2013-08-10]. http://people.csail.mit.edu/celiu/OpticalFlow/

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133