首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于Delaunay三角形网格立体图像编码算法的特征点提取
引用本文:杨嘉琛,侯春萍,徐然.基于Delaunay三角形网格立体图像编码算法的特征点提取[J].天津大学学报(自然科学与工程技术版),2009,42(5):424-427.
作者姓名:杨嘉琛  侯春萍  徐然
作者单位:天津大学电子信息工程学院,天津,300072  
基金项目:国家自然科学基金,国家高技术研究发展计划(863计划) 
摘    要:可变形网格是目前立体图像编码方法研究的一个新方向.在Delaunay三角形网格立体图像编码算法的基础上,提出了一种特征点选取方法该方法充分利用物体边缘进行特征点提取,建立Delaunay三角形时能根据物体的边缘分割物体,以便能更好地反映物体复杂运动与形变PSNR值与实际观测结果表明,所提出的方法优于传统方法,更能够反映图像中物体运动和形变的细节

关 键 词:立体图像  图像编码  三角形网格  视差估计  边缘检测

A Feature-Node Selection Method Based on Delaunay Triangular Mesh Stereo Image Coding
YANG Jia-chen,HOU Chun-ping,XU Ran.A Feature-Node Selection Method Based on Delaunay Triangular Mesh Stereo Image Coding[J].Journal of Tianjin University(Science and Technology),2009,42(5):424-427.
Authors:YANG Jia-chen  HOU Chun-ping  XU Ran
Institution:(School of Electronic Information Engineering, Yianjin University, Tianjin 300072, China)
Abstract:A new development in stereo image coding research is the application of a deformable mesh. Based on the Delaunay triangular mesh stereo image coding algorithm,a feature-node selection method was proposed in this paPer, which made full use of the edge of objects to select feature nodes. At the establishment of the Delaunay triangular grid, the objects could be parted according to their edges,so as to better reflect the complex movement and deformation of the objects. PSNR value and observations show that the proposed method is superior to the traditional ones,reflecting the details of movement and deformation of the objects much better.
Keywords:stereo image  image coding  triangular mesh  disparity estimation  edge detection
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号