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.