메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
김정효 (한국과학기술원) 노용만 (한국과학기술원)
저널정보
대한전자공학회 대한전자공학회 학술대회 2019년도 대한전자공학회 추계학술대회 논문집
발행연도
2019.11
수록면
305 - 309 (5page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Infrared based camera can capture images that spatially distributed wavelength in the infrared band. So images can be obtained even when the visible ray based camera is not working. Infrared image is used in many fields such as national defense, disaster response, aviation, satellite that are closely related to human life. However, since infrared radiation is absorbed and scattered by water vapor components in the atmosphere, it is very difficult to obtain clear infrared images in inclement weather conditions such as haze and rainfall. Given the role and weakness of infrared based equipment, obtaining clear infrared images that are less affected by weather conditions is very important. Previous studies has limitations that need clear image of the same scene in training phase. In this paper, we propose a method to improve the single infrared image by eliminating fog to solve the above problem. Using generators that receive images from one domain and generates images of another domain, discriminators that determine the domain of the generated images, and a perceptual feature extractor that takes into account cognitive characteristics, we can convert blurry images into clearer images without using image pairs for exactly the same scene on cloudy and sunny days. In order to verify the proposed method, experiments using real infrared images taken on cloudy and sunny days have been carried out and the proposed method is confirmed to obtain clear infrared images from the infrared images taken in inclement weather conditions.

목차

Abstract
I. 서론
II. 본론
Ⅲ. 구현 및 실험 결과
Ⅳ. 결론
참고문헌

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2020-569-000090915