一种SAR与可见光图像压缩感知融合增强方法

A SAR and Electro-optical Images Fusion Algorithm Based on Compressed Sensing and Enhancement

针对机载多传感器成像战场态势感知的问题,提出了一种合成孔径雷达(Synthetic Aperture Radar,SAR)与可见光图像压缩感知融合增强方法。该方法首先对SAR与可见光图像分别进行压缩感知测量,得到压缩测量值,然后通过基于局部权值的融合方法实现对压缩测量值的融合,再利用有序度最优分割法提取SAR图像的强散射目标,最后对融合测量值重建得到初步融合图像,初步融合图像通过目标对比度增强得到最终融合图像。对多组图像进行了仿真分析,视觉及数值结果表明该方法能显著增强融合图像的目标对比度,提升了图像纹理清晰度,较大程度降低了图像融合过程中的数据计算量。

Due to the problem of multi-sensor imaging for battlefield situational awareness in air-based platform,a synthetic aperture radar(SAR) and electro-optical(EO) images fusion algorithm based on compressed sensing and enhancement is proposed.Firstly,the SAR and EO images are measured independently by compressed sensing to get the compressed measurements.Secondly,the measurements are fused using the local weight value fusion method,and the strong scattering target of SAR image is obtained through the segmentation method of optimal order-degree.Finally,the ultimate fusion image is obtained using the compressed sensing reconstructing algorithm and target contrast enhancement.Numerical experiments of several images demonstrate that this method has stronger target contrast,higher texture sharpness and much lower data calculation cost compared with other existing schemes.