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
학술저널
저자정보
Lee, Yeseok (Seoul National University) Kim, Yongil (Seoul National University)
저널정보
한국측량학회 한국측량학회지 한국측량학회지 제41권 제3호
발행연도
2023.6
수록면
191 - 201 (11page)
DOI
10.7848/ksgpc.2023.41.3.191

이용수

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

초록· 키워드

오류제보하기
SWIR (short-wave infrared) imaging provides unique information by penetrating foggy or smoky areas. However, interpreting SWIR images can be visually challenging owing to their wavelength ranges differing from those of visible light. Existing colorization models are primarily designed for visible-light wavelength bands, which limits their direct application to satellite images that encompass diverse wavelength bands. In this paper, we propose two approaches for colorizing SWIR images obtained from Worldview-3. The first approach is to generate a panchromatic image from the SWIR image and inputting it into pre-trained models to obtain a color image. The second approach is to obtain a color image directly from the SWIR image using a convolutional neural network-based model. Experimental results demonstrated that training the model to generate color images directly from SWIR images performed better than using pre-trained models. The consideration of spectral information also visually improved the performance, which was further confirmed by quantitative metrics. Additionally, the application of colorization to regions where color images were unavailable owing to factors such as smoke yielded improved visual identification compared to SWIR images.

목차

Abstract
1. Introduction
2. Materials
3. Methodology
4. Experimental results and discussion
5. Conclusion
References

참고문헌 (20)

참고문헌 신청

함께 읽어보면 좋을 논문

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

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0102-2023-533-001743366