Multisensor data fusion technology has been widely used in remote sensing image processing. Aiming at the problem of low spatial resolution of remote sensing multispectral images, a multiresolution image fusion method based on normalized correlation moment is proposed. This method first performs two-dimensional wavelet transform on the image, and then defines the local grayscale correlation moment of the image according to the first-order and second-order statistical characteristics of the high-frequency wavelet coefficients. This method is used as the image fusion measure to perform multiresolution feature fusion on the remote sensing image, thereby obtaining a fused image containing more information and effective features. Simulation results show that the fused image can achieve good results in retaining multispectral information and improving spatial resolution, so it can be better used in remote sensing image processing such as target recognition and classification. Keywords Data fusion Multiresolution image fusion Correlation moment Remote sensing image processing Abstract Multisensor data fusion technique has been widely used in remote sensing image processing. A major problem in using remote sensing multispectral images is the low spatial resolution. In order to improve spatial resolution, the image processing method can be used to improve the spatial resolution of the image. lut ion of the multispectral images, a multireflection image fusion method based on the normalized correlation moment is proposed in this paper. After 22D wavelet transformation, the normalized correlation moment is defined by means of statistical first2o rder and second2o rdermoment of the sew avelet coefficients with high frequency component under different reso lut ions. By using the local correlation moment asmeasure of feature selection, the new method carries out multireflection image fusion. And the fused images include more useful information for further application. Experiments are conducted on Landsat TM and SPO T data. Computer simulations show that the fused images obtain better results in terms of both p Keywords Data fusion, Multidimensional image fusion, Color moment, Remote sensing image processing
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore