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
Kyeong Soo Jeong (Chungbuk National University) Seong Hwan Go (Chungbuk National University) Won Ki Jo (Chungbuk National University) Jong Hwa Park (Chungbuk National University)
저널정보
충남대학교 농업과학연구소 Korean Journal of Agricultural Science Korean Journal of Agricultural Science Vol.52 No.1
발행연도
2025.3
수록면
51 - 65 (15page)

이용수

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

초록· 키워드

오류제보하기
Early and accurate detection of missing and low-vigor plants is crucial for optimizing crop yields and resource use in agriculture. Traditional manual scouting methods are time-consuming and labor-intensive. This study addresses the need for a rapid and efficient solution for assessing stand establishment in cabbage crops. This research presents a simplified image analysis pipeline for the early detection of missing and low-vigor cabbage plants using unmanned aerial vehicle (UAV) RGB imagery and a deep learning-based object detection model. The system employs a Faster region-based convolutional neural networks (R-CNN) model with a ResNet-50 feature pyramid network (FPN) backbone for plant detection. A streamlined preprocessing workflow, incorporating feature extraction using ResNet-50 FPN, enhances image contrast. Plant vigor is assessed using a computationally efficient, area-based classification method, with the 30th percentile of predicted bounding box areas serving as the threshold between “healthy” and “low-vigor” plants. This threshold was determined through visual assessment and iterative testing. Missing plants (also known as “knots”) are identified by comparing detected plant locations with a grid of expected planting positions, generated from known planting patterns and refined by removing overlaps with detected plants. The Faster R-CNN model achieved an F1-score of 0.90 on a test dataset (using a confidence score threshold of 0.7). A field trial in a Smart Organic Farming Demonstration Complex in Goesan-gun, South Korea, revealed a significant stand establishment issue: a missing plant rate of 54.81% and 13.19% of plants classified as low-vigor. The developed system, combining UAV RGB imagery, deep learning, and simplified image analysis, offers a practical and efficient solution for precise crop monitoring. Visualizations and a geo-referenced planting map provide actionable information for targeted replanting. This research demonstrates significant advancements over traditional methods, paving the way for more sustainable and resilient agricultural practices by enabling timely intervention to minimize yield loss in the critical early stages of cabbage growth.

목차

Abstract
Introduction
Materials and Methods
Results and Discussion
Conclusion
References

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

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-151-25-02-092508452