Multi-source heterogeneous remote sensing image fusion method

Abstract

The invention discloses a multi-source heterogeneous remote sensing image fusion method, which comprises the following steps of: firstly, selecting a high-resolution remote sensing image and an unmanned aerial vehicle aerial photo image in the same area, performing orthographic correction and image registration preprocessing on the high-resolution remote sensing image and the unmanned aerial vehicle aerial photo image, and fusing a multispectral image (MSS) and a panchromatic image (PAN) of the high-resolution remote sensing image by adopting a GS (Gram-Schmidt) algorithm; performing HIS transformation on the GS image to obtain three components of brightness (I1), chromaticity (H1) and saturation (S1), and then performing waveband decomposition on an unmanned aerial vehicle (UAV) aerial photo image by adopting a Laurous wavelet algorithm to obtain wavelet surfaces with different resolutions; and superposing each wavelet surface in the PAN image to obtain a fused image UAP, carrying out HIS conversion on the UAP to obtain corresponding brightness (I2), chroma (H2) and saturation (S2) components, replacing the brightness component I1 of the GS image with the brightness component I2 of the UAP image, and carrying out HIS inverse conversion on the I2, H1 and S1 components to obtain a fused image.

Description

technical field [0001] The invention belongs to the field of remote sensing image processing data fusion, and in particular relates to a fusion method of multi-source heterogeneous remote sensing images. Background technique [0002] With the rapid development of modern remote sensing technology, the acquisition methods of remote sensing data are increasing continuously. Due to the different imaging principles of similar remote sensing data and the limitations of technical conditions, any single image source cannot fully reflect the characteristics of the target object, and it is difficult to have the characteristics of high spatial and high spectral resolution at the same time. Therefore, the application has certain limitations. In order to make full use of these rich image data, the required information is mined from different image data. In order to have a more comprehensive, clear and accurate understanding and cognition of the observation target, remote sensing images...

AI Technical Summary

Problems solved by technology

[0003] From the perspective of fusion principles, it can be roughly divided into fusion methods based on signal analysis principles, fusion methods based on color space theory, fusion methods based on mathematical statistical analysis, and four arithmetic operations. However, traditional remote sensing image fusion methods such as: principal component analysis (PCA) , HIS transformation fusion, CN fusion and other methods have certain limitations in the fusion of multi-source heterogeneous images, and cannot improve the resolution and spatial detail performance of the fusion image.

Images