面向地物混杂背景的偏振光谱图像融合方法  

Polarization spectral image fusion method for hybrid backgrounds of ground objects

作　　者：李英超[1] 赵喆浩 王祺 刘嘉楠 史浩东[1,2] 付强[1,2] 孙洪宇 LI Ying-chao;ZHAO Zhe-hao;WANG Qi;LIU Jia-nan;SHI Hao-dong;FU Qiang;SUN Hong-yu(Jilin Provincial Key Laboratory of Space Optoelectronics Technology,Changchun University of Science and Technology,Changchun 130022,China;School of Optoelectronic Engineering,Changchun University of Science and Technology,Changchun 130022,China)

机构地区：[1]长春理工大学空间光电技术研究所,吉林长春130022 [2]长春理工大学光电工程学院,吉林长春130022

出　　处：《中国光学（中英文）》2024年第5期1098-1111,共14页Chinese Optics

基　　金：国家自然科学基金(No.61890960)。

摘　　要：针对偏振光谱图像融合方法在地物混杂背景遥感探测中多尺度变换融合图像存在边缘轮廓细节模糊、对比度不佳的问题,提出一种基于非下采样轮廓波变换的稀疏表示与引导滤波器相结合的图像融合方法,以改善融合图像的质量和视觉效果。首先,该方法通过非下采样轮廓波变换对光谱图像和偏振图像进行多尺度多方向分解,进而将图像分解成不同子带内的特征信息。其次,低频子带采用稀疏表示融合,从而降低融合图像中物体对比度损失。此外,采用引导滤波器融合高频子带,以增强图像轮廓细节信息。最后,对低频与高频融合系数进行非下采样轮廓波逆变换,最终得出融合图像。分析表明融合图像对比度相对于原始光谱图像与偏振度图像分别提升了54.5%和15.4%,更容易区分混杂背景下阴影中的物体。基于此方法对偏振光谱成像仪所采集的不同波长下的光谱与偏振图像进行融合,并实现真彩还原。真彩还原图像证明此融合方法在保留混杂背景下的环境信息的同时实现了物体和背景的有效区分,有效提高了偏振光谱遥感探测成像的图像质量,有助于提升偏振光谱遥感探测成像中图像信息的完整性和真实性,扩大其在复杂环境遥感探测和图像识别中的应用范围。To address the issues of blurred edge details and poor contrast in multi-scale transform fused images obtained using remote sensing detection methods for mixed background features,an image fusion method that combines the sparse representation of non-downsampled contour wavelet transform and a guided filter 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 polarimetric images using non-downsampled contour wavelet transform to isolate the feature information in each subband;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 distinguish 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 reproduction.These true-colour restored images demonstrate that this fusion method retains environmental information within the mixed background while distinguishing the object from the background,effectively improving the image quality of polarization spectral remote sensing detection imaging.This method can enhance 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.

关 键 词：遥感探测成像 偏振图像 光谱图像 图像融合 非下采样轮廓波变换 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]