基于图割和视域相关性的立体图像分割.pdf

研究与开发
基于图割和视域相关性的立体图像分割
戴庆焰2,朱仲杰2
(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4590)
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 rabaut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。
关键词:立体图像分割;改进 Grabcu算法;视域相关性;轮廓匹配
doi:10.1959/is.100801.2015226
Stereo Image Segmentation Based on Graph
Cut and Visual Correlation
Dai Qin
long)le
(1. Ningbo Key Lab of DSP, Zhejiang Wanli University,, Ningbo 315100, China;
2. Physical Engineering College, Zhengzhou University, Zhengzhou 450001, China
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 lic 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
Key words: stereo image segmentation, improved Grabcut algorithm, inter-view correlation, contour correspondence
收稿日期:2015-06-14;修回日期:2015-09-06
基金项目:国家自然科学基金资助项目(No.6090206)浙江省自然科学基金资助项目(No.LY14FO10060,宁波市自然基金资助
项目(No.2015A610136),人社部留学科技人员择优资助项目(No.2013-27,教育部留学回国人员科研启动基金资助项目(Na.2014-1685
Foundation Items: The National Natural Science Foundation of hina(N. 6090206, The Natural Science Foundation of Zhejiang
Province(No Y14F01000 Ningbo Municipal Natural Science Fund i(N.2015A61013 T Scien if Activitie Foundation for Selecte
Returned Overseas Professionals of Human Resources and ocial Security Minist(N. 2013-277, The Scientific Research Foundation for the
Returned Overseas Chinese Scholars, State Education Ministry(No. 2014-1685)
论文引用格式:戴庆焰,朱仲杰.基于图割和视域相关性的立体图像分割.电信科学,2015226
Dai Q Y, Zhu Z J Stereo image segmentation based on graph cut and visual correlation. Telecommunications Science, 2015226
2015226
万方数据