Research on Clearance of Aerial Remote Sensing Images Based on Image Fusion

Abstract

Dark channel prior defogging algorithm can not only effectively remove the influence of clouds on the aerial remote sensing images, but also bring incomplete defogging to compensate the lack of image details recovery or even covering and so on. In order to slove this problem, an image fusion scheme is proposed in this paper. Based on the combination of the dark channel prior and guided filtering, the LOG edge detection features of the original images and defogging results will be fused at a certain proportion. Through the experimental analysis and comparison of a large number of remote sensing images, we find that the amount of image information becomes larger after fusion and the percentage of entropy reaches a maximum value and then decreases as the fusion ratio increases . In view of this, the optimal fusion ratio of the images is determined. Based on the subjective and objective evaluation results of the image quality, the correctness and validity of the method are verified. Therefore, this method not only removes the clouds effectively, but also retains the details of the original images to achieve the purpose of image clearness.