摘要
针对多光谱图像和全色图像融合问题,提出了一种基于稀疏表示的多光谱与全色遥感图像融合新方法。首先对多光谱图像进行IHS变换,得到I亮度分量,然后采用滑动窗口技术对I亮度分量和全色图像分块,利用过完备字典和正交匹配算法(OMP)得到I亮度分量和全色图像的稀疏系数,采用Sigmoid函数对稀疏系数进行融合。文中使用Quick Bird卫星数据验证本文提出方法的有效性。实验结果表明,相比于传统方法,本文方法得到的融合图像具有较好的光谱特性,保留了更多的空间细节信息。
A new fusion method of multi-spectral image and panchromatic remote sensing image base on sparse representation is proposed as follows.Firstly,the multi-spectral image is converted to IHS,which produces an array of luma samples,and then the sliding window technique is used to divide the panchromatic image and one array of luma samples into pieces.The complete dictionary is combined with OMP algorithm to extract sparse coefficients for the panchromatic image and one array of luma samples.Sigmoid function is used to fuse the sparse coefficients.QuickBird satellite data verify the effectiveness of the above method.The proposed method can keep better spectral properties and more spatial information of the fused image in comparison with traditional method.
作者
高瑞超
雷力军
张存柱
Gao Ruichao;Lei Lijun;Zhang Cunzhu(CCCC First Harbor Consultants Co.,Ltd.,Tianjin 300222,China)
出处
《港工技术》
2019年第2期113-115,共3页
Port Engineering Technology
关键词
多光谱图像
全色图像
图像融合
稀疏表示
SIGMOID函数
multi-spectral image
panchromatic image
fusion of images
sparse representation
Sigmoid function
