邰建豪, 潘斌, 赵珊珊, 赵园. 基于Shearlet变换的SAR与多光谱遥感影像融合[J]. 武汉大学学报 ( 信息科学版), 2017, 42(4): 468-474. DOI: 10.13203/j.whugis20150768
引用本文: 邰建豪, 潘斌, 赵珊珊, 赵园. 基于Shearlet变换的SAR与多光谱遥感影像融合[J]. 武汉大学学报 ( 信息科学版), 2017, 42(4): 468-474. DOI: 10.13203/j.whugis20150768
TAI Jianhao, PAN Bin, ZHAO Shanshan, ZHAO Yuan. SAR and Multispectral Remote Sensing Image Fusion Method Using Shearlet Transform[J]. Geomatics and Information Science of Wuhan University, 2017, 42(4): 468-474. DOI: 10.13203/j.whugis20150768
Citation: TAI Jianhao, PAN Bin, ZHAO Shanshan, ZHAO Yuan. SAR and Multispectral Remote Sensing Image Fusion Method Using Shearlet Transform[J]. Geomatics and Information Science of Wuhan University, 2017, 42(4): 468-474. DOI: 10.13203/j.whugis20150768

基于Shearlet变换的SAR与多光谱遥感影像融合

SAR and Multispectral Remote Sensing Image Fusion Method Using Shearlet Transform

  • 摘要: 针对合成孔径雷达(SAR)影像和多光谱遥感影像在融合时空间特征和光谱特征方面不能同时得到较大改善的问题,提出了一种基于成像特性的Shearlet变换域下的多源遥感影像融合方法。利用Shearlet变换的多方向和多尺度分解特性,将多光谱影像和SAR影像分别分解为高频和低频系数,从影像区域能量特征和区域相关性入手,设计了基于区域能量的低频系数融合规则和改进型的脉冲耦合神经网络的高频系数融合规则,使融合结果能够包含更多空间细节信息和光谱信息。利用TerraSAR-X、Landsat5-TM影像进行实验,结果表明该方法在提高影像空间细节表达能力的同时能够较好地融合更多的光谱信息。与小波变换、非下采样轮廓波变换(Nonsubsampled contourlet Transform,NSCT)等方法相比,该方法在空间信息保有量和光谱信息保有量方面都有明显的提升,其中交叉熵有接近100%的提升幅度,互相关系数有高于25%的提升幅度,光谱扭曲度有优于40%的提升幅度。

     

    Abstract: In terms of conventional methods for SAR image and multispectral image fusion can't integrate and reserve good spectral information and spatial resolution at the same time, a new fusion method based on the difference of imaging mechanism of SAR and multispectral images is proposed in this paper. Firstly, the original image is decomposed by Shearlet transform, and the high frequency and low frequency components are obtained respectively. The two components contain different detailed information of the image. Shearlet transform decomposes the image into multi-scale and multi-directional sub-band coefficients, which contain different image features. In addition, Shearlet inverse transform has good image reconstruction capability. And then, according to that the low frequency coefficient and the high frequency coefficient represent different meanings, we design the different fusion rule for them. The fusion rules of low frequency coefficients based on region energy and the high frequency coefficient based on improved pulse coupled neural network are designed. Finally, an information-rich image is obtained by inversing Shearlet transform. Therefore, the fusion results are richer and contain more spatial detail information and spectral information. In order to verify the effectiveness of the proposed method, a test is carried out with data from TerraSAR-X and Landsat5-TM, and the result shows that the proposed method is effective in improving the spatial resolution and keeping more spectral information. Compared with the methods of wavelet transform, contourlet transform, and NSCT transform, this method has a significant improvement in spatial information and spectral information. Cross entropy has a margin of improvement of nearly 100%. The correlation coefficient is higher than 25% increase, and the spectral distortion is better than 40% increase.

     

/

返回文章
返回