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

논문 기본 정보

자료유형
학술저널
저자정보
고승환 (충북대학교) 박종화 (충북대학교)
저널정보
대한원격탐사학회 대한원격탐사학회지 대한원격탐사학회지 제40권 제1호
발행연도
2024.2
수록면
93 - 101 (9page)
DOI
https://doi.org/10.7780/kjrs.2024.40.1.9

이용수

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

초록· 키워드

오류제보하기
Accurate field crop classification is essential for various agricultural applications, yet existingmethods face challenges due to diverse crop types and complex field conditions. This study aimed toaddress these issues by combining support vector machine (SVM) models with multi-seasonal unmannedaerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix(GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March–October2021, while field surveys on three dates provided ground truth data. We focused on data from August(-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models(SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided bythe Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identificationand served as a reference for accuracy comparison. Our analysis showcased the significant impact ofhyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization foreach scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-Otrained on October data achieving the highest overall and individual crop classification accuracy. Thissuccess likely stems from its ability to capture distinct texture information from mature crops. IncorporatingGLCM features proved highly effective for all models, significantly boosting classification accuracy. Amongthese features, homogeneity, entropy, and correlation consistently demonstrated the most impactfulcontribution. However, balancing accuracy with computational efficiency and feature selection remainscrucial for practical application. Performance analysis revealed that SVC-O achieved exceptional resultsin overall and individual crop classification, while soybeans and rice were consistently classified well byall models. Challenges were encountered with cabbage due to its early growth stage and low field coverdensity. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunctionwith SVM models for accurate field crop classification. Careful parameter tuning and model selectionbased on specific scenarios are key for optimizing performance in real-world applications.

목차

등록된 정보가 없습니다.

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

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

최근 본 자료

전체보기

댓글(0)

0