中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 三维可视计算
Interactive stereo image segmentation via adaptive prior selection

文献类型：期刊论文

作者Ma, Wei1; Qin, Yue1; Xu, Shibiao2; Zhang, Xiaopeng2
刊名MULTIMEDIA TOOLS AND APPLICATIONS
出版日期2018-11-01
卷号77期号:21页码:28709-28724
关键词Stereo image segmentation Interactive segmentation Prior selection Multi-label MRF Graph cut
ISSN号1380-7501
DOI10.1007/s11042-018-6067-5
通讯作者Xu, Shibiao(shibiao.xu@ia.ac.cn) ; Zhang, Xiaopeng(xiaopeng.zhang@ia.ac.cn)
英文摘要Interactive stereo image segmentation (i.e., cutting out objects from stereo pairs with limited user assistance) is an important research topic in computer vision. Given a pair of images, users mark a few foreground/background pixels, based on which prior models are formulated for labeling unknown pixels. Note that color priors might not help if the marked foreground and background have similar colors. However, integrating multiple types of priors, e.g., color and disparity in segmenting stereo pairs, is not trivial. This is because differing pairs of images and even differing pixels in the same image might require different proportions of the priors. Besides, disparities of natural images are too noisy to be directly used. This paper presents a method that can adaptively determine the proportion of the priors (color or disparity) for each pixel. Specifically speaking, the segmentation problem is defined in the framework of MRF (Markov Random Field). We formulate an MRF energy function which is composed of clues from the two types of priors, as well as neighborhood smoothness and stereo correspondence constraints. The weights of the color and disparity priors at each pixel are treated as variables which are optimized together with the label (foreground or background) of the pixel. In order to overcome the noise problem, the weight of the disparity prior is controlled by a confidence value learned from data. The energy function is optimized by using multi-label graph cut. Experimental results show that our method performs well.
WOS关键词GRAPH CUTS
资助项目National Natural Science Foundation of China[61771026] ; National Natural Science Foundation of China[61379096] ; National Natural Science Foundation of China[61671451] ; National Natural Science Foundation of China[61502490] ; Scientific Research Project of Beijing Educational Committee[KM201510005015] ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR)[4152006] ; Beijing Municipal Natural Science Foundation[4152006]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000446601500038
出版者SPRINGER
资助机构National Natural Science Foundation of China ; Scientific Research Project of Beijing Educational Committee ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) ; Beijing Municipal Natural Science Foundation
源URL[http://ir.ia.ac.cn/handle/173211/23049]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Xu, Shibiao; Zhang, Xiaopeng
作者单位1.Beijing Univ Technol, Fac Informat Technol, 100 Pingleyuan St, Beijing 100124, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Ma, Wei,Qin, Yue,Xu, Shibiao,et al. Interactive stereo image segmentation via adaptive prior selection[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2018,77(21):28709-28724.
APA Ma, Wei,Qin, Yue,Xu, Shibiao,&Zhang, Xiaopeng.(2018).Interactive stereo image segmentation via adaptive prior selection.MULTIMEDIA TOOLS AND APPLICATIONS,77(21),28709-28724.
MLA Ma, Wei,et al."Interactive stereo image segmentation via adaptive prior selection".MULTIMEDIA TOOLS AND APPLICATIONS 77.21(2018):28709-28724.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。