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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Stereo superpixel: An iterative framework based on parallax consistency and collaborative optimization

文献类型：期刊论文

作者Li, Hua2,3,4; Cong, Runmin1,5; Kwong, Sam2; Chen, Chuanbo3; Xu, Qianqian6; Li, Chongyi7
刊名INFORMATION SCIENCES
出版日期2021-05-01
卷号556页码:209-222
关键词Stereo superpixel Superpixel segmentation Parallax consistency Collaborative optimization
ISSN号0020-0255
DOI10.1016/j.ins.2020.12.031
英文摘要Stereo superpixel segmentation aims to obtain the superpixel segmentation results of the left and right views more cooperatively and consistently, rather than simply performing independent segmentation directly. Thus, the correspondence between two views should be reasonably modeled and fully considered. In this paper, we propose a left-right interactive optimization framework for stereo superpixel segmentation. Considering the disparity in stereo image pairs, we first divide the images into paired region and non-paired region, and propose a collaborative optimization scheme to coordinately refine the matched superpixels of the left and right views in an interactive manner. This is, to the best of our knowledge, the first attempt to generate stereo superpixels considering the parallax consistency. Quantitative and qualitative experiments demonstrate that the proposed framework achieves superior performance in terms of consistency and accuracy compared with single-image superpixel segmentation. (C) 2020 Elsevier Inc. All rights reserved.
资助项目Key Project of Science and Technology Innovation 2030 - Ministry of Science and Technology of China[2018AAA0101301] ; Natural Science Foundation of China[61772344] ; Natural Science Foundation of China[62002014] ; Hong Kong RGC General Research Funds[9042816] ; Hong Kong RGC General Research Funds[CityU 11209819] ; Beijing Nova Program[Z201100006820016] ; Fundamental Research Funds for the Central Universities[2019RC039] ; Elite Scientist Sponsorship Program by Beijing Association for Science and Technology ; Hong Kong Scholars Program ; China Postdoctoral Science Foundation[2020T130050] ; China Postdoctoral Science Foundation[2019M660438]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000626586900013
出版者ELSEVIER SCIENCE INC
源URL[http://119.78.100.204/handle/2XEOYT63/16794]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Cong, Runmin; Kwong, Sam
作者单位1.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China
2.City Univ Hong Kong, Dept Comp Sci, Kowloon, Hong Kong, Peoples R China
3.Huazhong Univ Sci & Technol, Sch Software Engn, Wuhan 430074, Peoples R China
4.Hainan Univ, Sch Comp Sci & Cyberspace Secur, Haikou 570228, Hainan, Peoples R China
5.Beijing Jiaotong Univ, Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China
6.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100864, Peoples R China
7.Nanyang Technol Univ, Singapore 639798, Singapore
推荐引用方式
GB/T 7714		 Li, Hua,Cong, Runmin,Kwong, Sam,et al. Stereo superpixel: An iterative framework based on parallax consistency and collaborative optimization[J]. INFORMATION SCIENCES,2021,556:209-222.
APA Li, Hua,Cong, Runmin,Kwong, Sam,Chen, Chuanbo,Xu, Qianqian,&Li, Chongyi.(2021).Stereo superpixel: An iterative framework based on parallax consistency and collaborative optimization.INFORMATION SCIENCES,556,209-222.
MLA Li, Hua,et al."Stereo superpixel: An iterative framework based on parallax consistency and collaborative optimization".INFORMATION SCIENCES 556(2021):209-222.

入库方式： OAI收割

来源：计算技术研究所

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。