摘要
提出了一种基于SUSAN算法自动消去主图像中云区遮挡影响的方法。该方法首先利用SUSAN算法有效提取主图像和参考图像中的角点,然后采用概率松弛法寻找主图像和参考图像间的匹配点,将主图像与参考图像配准,在此基础上搜索主图像的云区,最后进行融合得到去云图像。实验结果表明该方法具有较好的去云效果。
A new image fusion scheme that could automate remove the cloud covers in the main image was proposed based on SUSAN algorithm. First, the corners were found both in the main image and the reference image based on SUSAN algorithm, and then the matched corners were found using probabilistic relaxation algorithm to register the reference image to the main image. Finally, a cloud-removed image was obtained by fusion. The performance of the proposed scheme is demonstrated experimentally.
出处
《通信学报》
EI
CSCD
北大核心
2006年第8期160-164,共5页
Journal on Communications
关键词
去云
图像配准
SUSAN算法
概率松弛法
图像融合
cloud removal
image registration
SUSAN algorithm
probabilistic relaxation algorithm
image fusion
