| 王琦,胡小鹏,王凡.基于边缘响应和自相似的红外与可见光图像区域特征匹配方法[J].,2020,60(3):317-324 |
| 基于边缘响应和自相似的红外与可见光图像区域特征匹配方法 |
| Method of region feature matching of infrared and visible images based on edge response and self-similarity |
| |
| DOI：10.7511/dllgxb202003013 |
| 中文关键词: 自相似 边缘响应 区域匹配 红外与可见光图像 |
| 英文关键词: self-similarity edge response region matching infrared and visible images |
| 基金项目:国家科技重大专项资助项目(2018YFA0704605);“十三五”重大专项资助项目(2017ZX05064). |
|
| 摘要点击次数: 334 |
| 全文下载次数: 402 |
| 中文摘要: |
| 红外与可见光图像的匹配是计算机视觉中一项重要的研究课题.由于红外与可见光光谱的差异,图像之间的相似性较低,图像匹配正确率较低.根据红外与可见光图像区域形状相似特点,提出了一种基于边缘响应和自相似区域特征匹配方法.该方法首先计算红外与可见光图像的边缘响应并检测区域特征,然后提取区域形状并建立区域形状的自相似描述,最后对区域特征进行匹配.实验结果表明,该方法在特征检测可重复率和特征匹配准确率等方面均具有良好的性能. |
| 英文摘要: |
| Matching of infrared and visible images is an important research topic in the field of computer vision. Due to the difference of infrared and visible spectra, the similarity between the images is low, leading to the low accuracy of image matching. According to the similarity of region shapes in infrared and visible images, a method of region feature matching based on edge response and self-similarity is proposed. Firstly, edge responses of infrared and visible images are calculated to detect region features; secondly, region shapes are extracted and self-similar descriptions of region shapes are established; finally, region features are matched. Experimental results show that the proposed method has good performance in terms of feature detection repeatability and feature matching accuracy. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|