Multi-spectral remote image registration based on SIFT
Multi-spectral remote image registration based on SIFT
复制标题
DOI：
10.1049/el:20082477
复制
发表时间：
2008-01-17
影响因子：
1.1
通讯作者：
Yang, X.
中科院分区：
文献类型：
--
作者：
Yi, Z.;Zhiguo, C.;Yang, X.
由于多光谱遥感图像间的灰度差异较大，采用基于SIFT的配准算法对多光谱遥感图像进行配准时，SIFT关键点的误匹配数量会急剧增加。提出了关键点匹配的尺度约束准则，实验结果表明，该准则能显著提高匹配性能。
The number of incorrect matches of SIFT keypoints will sharply increase when the SIFT-based registration algorithm is adopted for pairs of multi-spectral remote images, owing to the significant difference in the image intensity between multi-spectral images. Scale restriction criteria for keypoint matching are proposed, and experimental results demonstrate that it will greatly improve match performance.