활용사례

활용 사례
제목 An Experiment on Image Restoration Applying the Cycle Generative Adversarial Network to Partial Occlusion Kompsat-3A Image
국/내외 국내 작성일 2022-04-05

An Experiment on Image Restoration Applying the Cycle Generative Adversarial Network to Partial Occlusion Kompsat-3A Image 첨부 이미지

This study presents a method to restore an optical satellite image with distortion and occlusion due to fog, haze, and clouds to one that minimizes degradation factors by referring to the same type of peripheral image. Specifically, the time and cost of re-photographing were reduced by partially occluding a region. To maintain the original image’s pixel value as much as possible and to maintain restored and unrestored area continuity, a simulation restoration technique modified with the Cycle Generative Adversarial Network (CycleGAN) method was developed. The accuracy of the simulated image was analyzed by comparing CycleGAN and histogram matching, as well as the pixel value distribution, with the original image. The results show that for Site 1 (out of three sites), the root mean square error and R2 of CycleGAN were 169.36 and 0.9917, respectively,showing lower errorsthan those for histogram matching (170.43 and 0.9896, respectively). Further, comparison of the mean and standard deviation values of images simulated by CycleGAN and histogram matching with the ground truth pixel values confirmed the CycleGAN methodology as being closer to the ground truth value. Even for the histogram distribution of the simulated images, CycleGAN was closer to the ground truth than histogram matching.

Key Words:Deep learning, CycleGAN, High-resolution satellite image

출처 대한원격탐사학회지
이전/이후 글
이전글 농경지 관측을 위한 KOMPSAT 대기보정 적용 및 평가
다음글 다음 글이 없습니다.

네팔:지진(2015-05-05)

영상 정보
카테고리 재난재해
위성정보 KOMPSAT-3
생성일 2015-03-24

세부정보

영상 세부 정보
ProductID K3_20150505073608_15817_06161210
국가(영문) Nepal
국가 네팔
지역 Pokhara
레벨 1R