面向地物混杂背景的偏振光谱图像融合方法OA北大核心CSTPCD

To address the issues of blurred edge details and poor contrast in multi-scale transform fused im-ages obtained using remote sensing detection methods for mixed background features,an image fusion meth-od that combines the sparse representation of non-downsampled contour wavelet transform and a guided fil-ter is utilised to enhance the quality and visual appearance of the fused images.This method involves several steps:firstly,a multi-scale and multi-directional decomposition is performed on both spectral and polarimet-ric images using non-downsampled contour wavelet transform to isolate the feature information in each sub-band;secondly,the low-frequency subbands are fused using a sparse representation to minimize the loss of contrast in the fused image;additionally,the high-frequency subbands are fused through a bootstrap filter to enhance the detail information and the contours of the image;finally,the low-frequency and high-frequency fusion coefficients are inverted using non-downsampled contour wavelet inversion to generate the final fused image.Analysis results indicate that the contrast of the fused image is improved by up to 54.5%and 15.4%respectively compared to the original spectral image and the polarimetric image,making it easier to distin-guish objects in shadows under a mixed background.This method is used to fuse spectral and polarimetric images captured by a polarimetric spectral imager at different wavelengths,which resulted in true-colour re-production.These true-colour restored images demonstrate that this fusion method retains environmental in-formation within the mixed background while distinguishing the object from the background,effectively im-proving the image quality of polarization spectral remote sensing detection imaging.This method can en-hance the integrity and authenticity of image information in polarization spectral remote sensing detection imaging,thereby expanding its application scope in remote sensing detection of complex environments and image recognition.