欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
作为立体视觉关键技术之一的立体匹配，一直都是视觉领域研究的热点和难点。本文提出了一种基于分割区域的BP立体匹配算法。首先对于输入图像对进行mean—shift分割，对于初始视差图，利用交叉检测，将分割区域分为可靠和非可靠区域。基于此区域信息，利用BP算法对初始视差进行优化。实验结果表明，采用本文改进的BP算法，可以获得精确度更高的视差图。
英文摘要：
As one of the crucial techniques in stereo vision, stereo matching has been a long hot topic and difficult problem. An improved stereo matching algorithm based BP in segment region is proposed in this paper. Firstly, the algorithm uses mean - shift segmentation for the input image. Then by using cross -checking for the initial disparity map, segment region is divided into reliable and unreliable regions. Finally based on above regional information, the initial disparity is optimized by using BP algorithm. The experimental results show that higher accuracy disparity map can be obtained by using this improved BP algorithm.
同期刊论文项目
同项目期刊论文
Stereoscopic Visual Attention Based Regional Bit Allocation Optimization for Multi-view Video Coding
期刊信息
位置：