| 一种基于RANSAC的柱面图像配准算法 |
| |
| 引用本文： | 刘相滨,邹北骥.一种基于RANSAC的柱面图像配准算法[J].湖南大学学报(自然科学版),2010,37(8):79-82. |
| |
| 作者姓名： | 刘相滨 邹北骥 |
| |
| 作者单位： | 1. 中南大学,信息科学与工程学院,湖南,长沙,410083;湖南师范大学,图像识别与计算机视觉研究所,湖南,长沙,410081
2. 中南大学,信息科学与工程学院,湖南,长沙,410083 |
| |
| 基金项目： | 湖南省博士后科研资助计划项目，国家自然科学基金资助项目，国家自然科学基金重大研究计划项目，教育部高等学校博士点基金，新教师基金，浙江大学计算机辅助设计与图形学国家重点实验室开发项目 |
| |
| 摘 要： | 提出了一种基于RANSAC的柱面图像配准算法.首先采用NCC算法对检测出来的Harris角点进行粗匹配,然后采用两次改进的RANSAC算法删除误配,提高正确匹配角点的数量,最后对仿射变换模型参数进行Levenberg-Marquardt非线性优化以进一步降低图像的配准误差.实验结果表明:通过一次改进RANSAC去错配后角点有效匹配率达到约99.2%,通过二次改进RANSAC去错配后角点有效匹配率达到约99.6%,与现有算法相比,在同等条件下获得了更高的匹配有效率.
|
| 关 键 词： | 图像处理 特征提取 图像配准 |
A RANSAC-Based Cylindrical Image Registration Algorithm |
| |
| LIU Xiang-bin and ZOU Bei-ji.A RANSAC-Based Cylindrical Image Registration Algorithm[J].Journal of Hunan University(Naturnal Science),2010,37(8):79-82. |
| |
| Authors: | LIU Xiang-bin and ZOU Bei-ji |
| |
| Institution: | (1. School of Information Science and Engineering, Central-south Univ, Changsha, Hunan410083, China; 2. Institute of Image Recognition and Computer Vision, Hunan Normal Univ, Changsha, Hunan410081, China) |
| |
| Abstract: | A RANSAC-based cylindrical image registration algorithm was presented. First, the algorithm makes a coarse matching for the detected Harris corner points by using the NCC algorithm. Then, it reduces the false matched pairs by the two pass of improved RANSAC algorithm to increase the number of right matched pairs. At last, it optimizes the affine transformation model parameters by using Levenberg-Marquardt algorithm to lower the registration error. Experiments have shown that the right matched ratio of Harris corner reaches 99.2% after one time of improved RANSAC, and reaches 99.6% after two times of improved RANSAC. Compared with the existing methods, it has achieved higher right matched ratio under similar conditions. |
| |
| Keywords: | RANSAC NCC |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《湖南大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《湖南大学学报(自然科学版)》下载免费的PDF全文 |
|
