무인기로 취득한 RGB 영상과 YOLOv5를 이용한 수수 이삭 탐지 = Sorghum Panicle Detection using YOLOv5 based on RGB Image Acquired by UAV System

다국어 초록 (Multilingual Abstract)

The purpose of this study is to detect the sorghum panicle using YOLOv5 based on RGB images acquired by a unmanned aerial vehicle (UAV) system. The high-resolution images acquired using the RGB camera mounted in the UAV on September 2, 2022 were split into 512×512 size for YOLOv5 analysis. Sorghum panicles were labeled as bounding boxes in the split image. 2,000images of 512×512 size were divided at a ratio of 6:2:2 and used to train, validate, and test the YOLOv5 model, respectively. When learning with YOLOv5s, which has the fewest parameters among YOLOv5 models, sorghum panicles were detected with mAP@50=0.845. In YOLOv5m with more parameters, sorghum panicles could be detected with mAP@50=0.844. Although the performance of the two models is similar, YOLOv5s (4 hours 35 minutes) has a faster training time than YOLOv5m (5 hours 15 minutes). Therefore, in terms of time cost, developing the YOLOv5s model was considered more efficient for detecting sorghum panicles. As an important step in predicting sorghum yield, a technique for detecting sorghum panicles using high-resolution RGB images and the YOLOv5 model was presented.

국문 초록 (Abstract)

본 연구는 수수의 수확량 추정을 위해 무인기로 취득한 RGB 영상과 YOLOv5를 이용하여 수수 이삭 탐지 모델을 개발하였다. 이삭이 가장 잘 식별되는 9월 2일의 영상 중 512×512로 분할된 2000장을 이용하여 모델의 학습, 검증 및 테스트하였다. YOLOv5의 모델 중 가장 파라미터가 적은 YOLOv5s에서 mAP@50=0.845로 수수 이삭을 탐지할 수 있었다. 파라미터가 증가한 YOLOv5m에서는 mAP@50=0.844로 수수 이삭을 탐지할 수 있었다. 두 모델의 성능이 유사하나 YOLOv5s (4시간 35분)가 YOLOv5m (5시간 15분)보다 훈련시간이 더 빨라 YOLOv5s가 수수 이삭 탐지에 효율적이라고 판단된다. 개발된 모델을 이용하여 수수의 수확량 예측을 위한 단위면적당 이삭 수를 추정하는 알고리즘의 기초자료로 유용하게 활용될 것으로 판단된다. 추가적으로 아직 개발의 초기 단계를 감안하면 확보된 데이터를 이용하여 성능 개선 및 다른 CNN 모델과 비교 검토할 필요가 있다고 사료된다.

참고문헌 (Reference)

• 1 MAFRA, "양정자료"
• 2 문현동 ; 류재현 ; 나상일 ; 장선웅 ; 신서호 ; 조재일, "무인기 기반 다중분광 영상을 이용한 벼 쓰러짐 영역의 특성 분석" 대한원격탐사학회 37 (37): 917-926, 2021
• 3 나상일 ; 박찬원 ; 소규호 ; 안호용 ; 이경도, "국내 작황 모니터링을 위한 무인항공기 적용방안" 대한원격탐사학회 34 (34): 829-846, 2018
• 4 Redmon, J., "You only look once: Unified, real-time object detection" 779-788, 2016
• 5 Du, Z., "Smallholder crop area mapped with a semantic segmentation deep learning method" 11 (11): 888-, 2019
• 6 Alzubaidi, L., "Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions" 8 (8): 1-74, 2021
• 7 Ranđelović, P., "Prediction of soybean plant density using a machine learning model and vegetation indices extracted from RGB images taken with a UAV" 10 (10): 1108-, 2020
• 8 David, E., "Plant detection and counting from high-resolution RGB images acquired from UAVs: comparison between deep-learning and handcrafted methods with application to maize, sugar beet, and sunflower"
• 9 "NICS"
• 10 "NICS"
• 11 "KMA"
• 12 Yang, S., "Integration of crop growth model and random forest for winter wheat yield estimation from UAV hyperspectral imagery" 14 : 6253-6269, 2021
• 13 Gonzalo-Martín, C., "Improving deep learning sorghum head detection through test time augmentation" 186 : 106179-, 2021
• 14 Zhang, Y., "High-precision wheat head detection model based on one-stage network and GAN model" 13 : 2022
• 15 Prasad, P. V., "Growth and production of sorghum and millets, Soils, plant growth and crop production"
• 16 KOSIS, "Grain Production"
• 17 Marsalis, M. A., "Dry matter yield and nutritive value of corn, forage sorghum, and BMR forage sorghum at different plant populations and nitrogen rates" 116 (116): 52-57, 2010
• 18 Stehr, N. J., "Drones: The newest technology for precision agriculture" 44 (44): 89-91, 2015
• 19 Tack, J., "Disaggregating sorghum yield reductions under warming scenarios exposes narrow genetic diversity in US breeding programs" 114 (114): 9296-9301, 2017
• 20 García-Martínez, H., "Digital count of corn plants using images taken by unmanned aerial vehicles and cross correlation of templates" 10 (10): 469-, 2020
• 21 Yang, F., "Deep learning-based method for detection of external air conditioner units from street view images" 13 (13): 3691-, 2021
• 22 Li, H., "Comparison of Deep Learning Methods for Detecting and Counting Sorghum Heads in UAV Imagery" 14 (14): 3143-, 2022
• 23 Ha, Y. D., "Characteristics of proteins in Italian millet, sorghum and common millet" 8 (8): 187-192, 2001
• 24 Zhao, J., "A wheat spike detection method in UAV images based on improved YOLOv5" 13 (13): 3095-, 2021
• 25 RDA, "A study on the Management and Profitability of Small Area Cultivated Crops" 2020
• 26 Bayraktar, E., "A low-cost UAV framework towards ornamental plant detection and counting in the wild" 167 : 1-11, 2020