| 基于SIFT特征匹配的监控图像自动拼接 |
| |
| 引用本文： | 张朝伟,周焰,吴思励,林洪涛.基于SIFT特征匹配的监控图像自动拼接[J].计算机应用,2008,28(1):191-194. |
| |
| 作者姓名： | 张朝伟 周焰 吴思励 林洪涛 |
| |
| 作者单位： | 空军雷达学院,信息与指挥自动化系,武汉,430019 |
| |
| 摘 要： | 针对不同摄像头的监控图像，提出了一种优化的SIFT特征匹配的监控图像自动拼接方法。在图像整合方面，通过高速提取SIFT特征描述符并进行稳定精确匹配，利用改进RANSAC算法去除错配，从而确定待拼接图像之间的变换参数；在图像融合方面，有效消除了颜色和光照差异，最终实现自动的无缝拼接系统。实验结果证明该方法对重叠区域小、形变大、有运动遮挡和噪声的监控图像有较完美的拼接效果。
|
| 关 键 词： | 图像配准 SIFT 图像拼接 RANSAC算法 |
| 文章编号： | 1001-9081(2008)01-0191-04 |
| 收稿时间： | 2007-08-10 |
| 修稿时间： | 2007年8月10日 |
Automatic mosaic of surveillance images based on SIFT feature matching |
| |
| ZHANG Chao-wei,ZHOU Yan,WU Si-li,LIN Hong-tao.Automatic mosaic of surveillance images based on SIFT feature matching[J].journal of Computer Applications,2008,28(1):191-194. |
| |
| Authors: | ZHANG Chao-wei ZHOU Yan WU Si-li LIN Hong-tao |
| |
| Affiliation: | ZHANG Chao-wei,ZHOU Yan,WU Si-li,LIN Hong-tao(Department of Information & Comm, Automation,Air Force Radar Academy,Wuhan Hubei 430019,China) |
| |
| Abstract: | In this paper, an improved Scale Invariant Feature Transform (SIFT) feature-based approach for efficient automatic mosaic surveillance images was proposed. In the image registration step, SIFT Feature was extracted efficiently and reliable matching was carried out, and Random Sample Consensus (RANSAC) was improved to guarantee stability and decide the transformation parameters of the images stitching. In the image fuse step, a radiometric and color compensation stage allows the development of an automatic a... |
| |
| Keywords: | image registration Scale Invariant Feature Transform (SIFT) image mosaic Random Sample Consensus (RANSAC) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
|
