基于图割和视域相关性的立体图像分割

戴庆焰; 朱仲杰

doi:10.11959/j.issn.1000-0801.2015226

您当前的位置：

首页 >

文章列表页 >

基于图割和视域相关性的立体图像分割

研究与开发 | 更新时间：2024-06-05

- 基于图割和视域相关性的立体图像分割
- Stereo Image Segmentation Based on Graph Cut and Visual Correlation
- 电信科学 2015年31卷第11期页码：77-84
- 作者机构：
  
  1. 浙江万里学院宁波市DSP重点实验室宁波 315100
  2. 郑州大学物理工程学院郑州 450001
- 作者简介：
  
  [ "戴庆焰，男，郑州大学与浙江万里学院联合培养硕士生，主要研究方向为2D 与3D视频编码与传输。" ]
  [ "朱仲杰[通信作者]，男，博士，浙江万里学院教授，郑州大学兼职硕士生导师，主要研究方向为2D 与3D 视频编码与传输、视频语义分析与检索等。" ]
- 基金信息：
  
  国家自然科学基金资助项目;The National Natural Science Foundation of China(60902066);浙江省自然科学基金资助项目;The Natural Science Foundation of Zhejiang Province(LY14F010006);宁波市自然基金资助项目;Ningbo Municipal Natural Science Foundation(2015A610136);人社部留学科技人员择优资助项目;The Scientific Activities Foundation for Selected Returned Overseas Professionals of Human Resources and Social Security Ministry(2013-277);教育部留学回国人员科研启动基金资助项目;The Scientific Research Foundation for the Returned Overseas Chinese Scholars,State Education Ministry(2014-1685)
- DOI：10.11959/j.issn.1000-0801.2015226
  中图分类号：
- 网络出版日期：2015-11，
  
  纸质出版日期：2015-11-20
- 稿件说明：
移动端阅览
戴庆焰, 朱仲杰. 基于图割和视域相关性的立体图像分割[J]. 电信科学, 2015,31(11):77-84.

Qingyan Dai, Zhongjie Zhu. Stereo Image Segmentation Based on Graph Cut and Visual Correlation[J]. Telecommunications science, 2015, 31(11): 77-84.
戴庆焰, 朱仲杰. 基于图割和视域相关性的立体图像分割[J]. 电信科学, 2015,31(11):77-84. DOI： 10.11959/j.issn.1000-0801.2015226.

Qingyan Dai, Zhongjie Zhu. Stereo Image Segmentation Based on Graph Cut and Visual Correlation[J]. Telecommunications science, 2015, 31(11): 77-84. DOI： 10.11959/j.issn.1000-0801.2015226.

摘要

立体图像分割是对象基立体图像处理中的关键和难点。基于改进Grabcut图割算法和视域相关性，提出一种新的立体图像分割算法。首先基于改进Slic方法将左图像转换成超像素图像，然后基于Grabcut框架通过重新定义能量函数对其分割以提取出左图像目标。最后，基于左右图像的视域相关性通过融合颜色和纹理特征的轮廓匹配提取右图像目标。实验结果表明，与现有方法相比，所提算法能获得更高的分割效率和更准确的分割结果。

Abstract

Stereo image segmentation is a crucial and difficult issue in the field of object-based stereo image processing.By improving the Grabcut algorithm and exploiting the inter-view correlations

a novel stereo image segmentation scheme was proposed.The original left image was firstly transformed into a super-pixel image by improving the Slic algorithm.Then the super-pixel image was segmented and the foreground object in the left image is extracted based on the framework of Grabcut

where the energy function was rebuilt.Finally

by exploiting the inter-view correlations between the left and the right images

the foreground object in the right image was obtained based on contour correspondence by fusing color and texture features.The experimental results show that the proposed algorithm is more efficient and can achieve better segmentation results than the existing methods.

关键词

Keywords

references

吕朝辉，王晖．基于改进分水岭算法的立体视频对象分割．光电子·激光， 2009 , 20 （ 9 ）: 1238 ～ 1242

Lv C H , Wang H . Stereoscopic video object segmentation based on improved watershed algorithm . Journal of Optoelectronics· Laser , 2009 , 20 （ 9 ）: 1238 ～ 1242

Ntalianis K S , Doulamis N D , Doulamis A D , et al . An active contour-based video object segmentation scheme for stereoscopic video sequence . Proceedings of the 10th Mediterranean Electrotechnical Conference （MELECON2000） , 2000 : 554 ～ 557

唐果，赵晓东，汪元美．三维医学图像分割与可视化研究．计算机学报， 1998 , 21 （ 3 ）: 204 ～ 209

Tang G , Zhao X D , Wang Y M . Three-dimensional medical image segmentation and visualization . Chinese Journal of Computers , 1998 , 21 （ 3 ）: 204 ～ 209

Ntalianis K S , Doulamis N D , Doulamis A D , et al . A feature point based scheme for unsupervised video object segmentation in stereoscopic video sequences . Proceedings of the IEEE International Conference on Multimedia and Expo（ICME 2000） , New York,USA , 2000 : 1543 ～ 1546

朱仲杰，郁梅，蒋刚毅．用于立体视频会议系统的立体对象分割与跟踪算法．计算机辅助设计与图形学学报， 2004 , 16 （ 3 ）: 307 ～ 312

Zhu Z J , Yu M , Jiang G Y . An algorithm of object segmentation and tracking for stereoscopic video conferencing system . Journal of Computeraided Design ＆ Computer Graphics , 2004 , 16 （ 3 ）: 307 ～ 312

Rother C , Kolmogorov V , Blake A . GrabCut:interactive foreground extraction using iterated graph cuts . ACM Transactions on Graphics , 2004 , 23 （ 3 ）: 309 ～ 314

Achanta R , Shaji A , Smith K , et al . Slic Superpixels . EPFL Technical Report , 2010

丁红，张晓峰．基于快速收敛Grabcut的目标提取算法．计算机工程与设计， 2012 , 33 （ 4 ）: 1477 ～ 1481

Ding H , Zhang X F . Object abstraction algorithm with fast Grabcut . Computer Engineering and Design , 2012 , 33 （ 4 ）: 1477 ～ 1481

徐秋平，郭敏，王亚荣．基于分水岭变换和图割的彩色图像快速分割．计算机工程， 2009 , 35 （ 19 ）: 210 ～ 212

Xu Q P , Guo M , Wang Y R . Fast color image segmentation based on watershed transform and graph cuts . Computer Engineering , 2009 , 35 （ 19 ）: 210 ～ 212

Boykov Y , Kolmogorov V . An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision . IEEE Transactions on PAMI , 2004 , 26 （ 9 ）: 1124 ～ 1137

Gonzalez R C , Woods R E ．数字图像处理（第三版）．北京：电子工业出版社， 2001

Gonzalez R C P , Woods R E . Digital Image Processing （ Third Edition ）. Beijing : Publishing House of Electronics Industry , Computer Engineering , 2001

Pei S C , Wang Y Y . Color invariant census transform for stereo matching algorithm . Proceedings of IEEE 17th International Symposium on Consumer Electronics . Hsinchu,China , 2013 : 209 ～ 210

Geusebroek J M , Boomgaard R V D , Smeulders A W M , et al . Color invariance . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2001 , 23 （ 12 ）: 1338 ～ 1350

Zhang T Y , Suen C Y . A fast parallel algorithm for thinning digital patterns . Communications of the ACM , 1984 , 27 （ 3 ）: 236 ～ 239

浏览量

568

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据