摘要
去除遥感图像中的薄云是图像处理中的常见难题。为了更好地对存在薄云的遥感图像进行薄云去除,提高薄云遥感图像的地物细节信息的可读性。提出了基于小波变换和单尺度Retinex结合的遥感薄云去除算法,先将遥感薄云图像进行小波分解,对分解的低频薄云部分进行抑制,高频信息部分进行强化,处理后进行小波重建,然后利用单尺度Retinex算法对重建后的遥感图像进行增强处理。最后利用平均灰度值,信息熵,标准差及平均梯度指标进行客观评价分析,结果表明,该方法可以在有效去除薄云的同时增强地面细节信息。
Removing thin clouds from remote sensing images is a common problem in image processing. In order to better remove the thin cloud from the remote sensing image and improve the readability of ground object details. In this paper,a combination of wavelet transform and single-scale Retinex algorithm is proposed for the remote-sensing thin cloud removal. Firstly,the image of the thin-cloud remote sensing is decomposed into a wavelet,and the low-frequen- cy thin-cloud part of the decomposition is suppressed,the high-frequency ground detail part is enhanced. After pro- cessing,wavelet reconstruction is carried out. Then single-scale Retinex algorithm is used to enhance the reconstructed remote sensing image. Finally,the average gray value,information entropy,standard deviation and the average gradient index are used for objective evaluation and analysis. The results show that this method can effectively remove the thin cloud and enhance the ground detail information at the same time.
作者
杨晓倩
贾振红
杨杰
Nikola KASABOV
YANG Xiaoqian;JIA Zhenhong;YANG Jie;Nikola Kasabov(College of Information Science and Engineering,Xinjiang University,Urumuqi 830046,China;Institute of Image Processing and Pattern Recognition,Shanghai Jiaotong University,Shanghai 200240,China;Knowledge Engineering and Discovery Research Institute,Auckland University of Technology,Auckland 1020,New Zealand)
出处
《激光杂志》
北大核心
2019年第10期77-80,共4页
Laser Journal
基金
国家自然科学基金(No.61665012)
教育部国际合作研究项目(No.2016-2196)
