본문 바로가기
KERD
논문

지도학습 알고리즘 기반 3D 노지 작물 구분 모델 개발

Development of 3D Crop Segmentation Model in Open-field Based on Supervised Machine Learning Algorithm

김동수|이상익|오부영|이종혁|서병훈|서예진|최원|정영준|Ahmed Fawzy
한국농공학회 (The Korean Society Of Agricultural Engineers)|2022.01|한국농공학회논문집 (Journal of the Korean Society of Agricultural Engineers)|제64권 제1호|pp. 15-26

1

조회

0

다운로드

1

인용

0

참고문헌

키워드

Artificial neural networksactivation functionflood forecastingReLUsigmoid
주제분류농학

초록

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important datasetfor various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manualway is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV imagesand developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models usingdifferent data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN(K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value,using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our modelperformance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach,while it also classified actual non-crop points (e.g. weeds) as crops

Abstract

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important datasetfor various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manualway is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV imagesand developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models usingdifferent data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN(K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value,using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our modelperformance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach,while it also classified actual non-crop points (e.g. weeds) as crops

참고문헌 (45)

  1. 안희란, "모바일폰 기반 스테레오 영상에서 산출된 3차원 정보의 정확도 분석", 방송공학회 논문지, 19(5), pp.677~686 (2014), 한국방송∙미디어공학회[DOI]
  2. Catalina Albornoz, "Trajectory design for efficient crop irrigation with a UAV", 2017 IEEE 3rd Colombian Conference on Automatic Control (CCAC), pp.1~6 (2017), IEEE
  3. Yiannis Ampatzidis, "Agroview: Cloud-based application to process, analyze and visualize UAV-collected data for precision agriculture applications utilizing artificial intelligence", Computers and Electronics in Agriculture, 174, pp.105457~ (2020), Elsevier BV[DOI]
  4. Pelin Angin, "AgriLoRa: A Digital Twin Framework for Smart Agriculture", Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 11(4), pp.77~96 (2020), 차세대 정보과학 및 기술연구회[DOI]
  5. M. Dian Bah, "Weeds detection in UAV imagery using SLIC and the hough transform", 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pp.1~6 (2017), IEEE
  6. Danilo Bzdok, "Machine learning: supervised methods", Nature Methods, 15(1), pp.5~6 (2018), Springer Science and Business Media LLC[DOI]
  7. Chiu, M. T., "Agriculture-vision : A large aerial image database for agricultural pattern analysis", 2020 IEEE, 2020, 2825~2835
  8. 최석근, "무인항공기와 딥러닝(UNet)을 이용한 소규모 농지의 밭작물 분류", 한국측량학회지, 38(6), pp.671~679 (2020), 한국측량학회[DOI]
  9. Lorenzo Comba, "Unsupervised detection of vineyards by 3D point-cloud UAV photogrammetry for precision agriculture", Computers and Electronics in Agriculture, 155, pp.84~95 (2018), Elsevier BV[DOI]
  10. Smart farm technology and market trend report, "Commercializations Promotion Agency for R&D Outcomes", 4~14 (2019)
  11. Lucas Costa, "A new visible band index (vNDVI) for estimating NDVI values on RGB images utilizing genetic algorithms", Computers and Electronics in Agriculture, 172, pp.105334~ (2020), Elsevier BV[DOI]
  12. Ana de Castro, "3-D Characterization of Vineyards Using a Novel UAV Imagery-Based OBIA Procedure for Precision Viticulture Applications", Remote Sensing, 10(4), pp.584~ (2018), MDPI AG[DOI]
  13. Hivi Ismat Dino, "Facial Expression Classification Based on SVM, KNN and MLP Classifiers", 2019 International Conference on Advanced Science and Engineering (ICOASE), pp.70~75 (2019), IEEE
  14. Dominic Fawcett, "Unmanned aerial vehicle (UAV) derived structure-from-motion photogrammetry point clouds for oil palm (<i>Elaeis guineensis<", i>) canopy segmentation and height estimation, 2019, pp.40(19), 7538~7560[DOI]
  15. Alessandro dos Santos Ferreira, "Weed detection in soybean crops using ConvNets", Computers and Electronics in Agriculture, 143, pp.314~324 (2017), Elsevier BV[DOI]
  16. Ch. Gée, "Crop", weed discrimination in perspective agronomic images, 2008, pp.60(1), 49~59[DOI]
  17. E. Raymond Hunt, "Acquisition of NIR-Green-Blue Digital Photographs from Unmanned Aircraft for Crop Monitoring", Remote Sensing, 2(1), pp.290~305 (2010), MDPI AG[DOI]
  18. Sylvain Jay, "In-field crop row phenotyping from 3D modeling performed using Structure from Motion", Computers and Electronics in Agriculture, 110, pp.70~77 (2015), Elsevier BV[DOI]
  19. F. M. Jiménez-Brenes, "Quantifying pruning impacts on olive tree architecture and annual canopy growth by using UAV-based 3D modelling", Plant Methods, 13(1) (2017), Springer Science and Business Media LLC[DOI]
  20. J. M. Jurado, "Multispectral Mapping on 3D Models and Multi-Temporal Monitoring for Individual Characterization of Olive Trees", Remote Sensing, 12(7), pp.1106~ (2020), MDPI AG[DOI]
  21. Mohamed Kerkech, "VddNet: Vine Disease Detection Network Based on Multispectral Images and Depth Map", Remote Sensing, 12(20), pp.3305~ (2020), MDPI AG[DOI]
  22. 김혁길, "VLBI 안테나와 모바일폰 카메라를 활용한 근접수치사진측량의 캘리브레이션 초기값 결정에 따른 3차원 정확도 분석", 한국측량학회지, 33(1), pp.31~43 (2015), 한국측량학회[DOI]
  23. 김계영, "UAV 영상분석 및 현장조사 자료를 연계한 채소주산지 재배현황맵 서비스 시스템", 대한공간정보학회지, 27(1), pp.33~41 (2019), 대한공간정보학회[DOI]
  24. 김삼근, "기상 데이터를 이용한 데이터 마이닝 기반의 산불 예측 모델", 한국산학기술학회논문지, 21(8), pp.521~529 (2020), 한국산학기술학회[DOI]
  25. Huan Long, "Analysis of daily solar power prediction with data-driven approaches", Applied Energy, 126, pp.29~37 (2014), Elsevier BV[DOI]
  26. Adam Mathews, "Visualizing and Quantifying Vineyard Canopy LAI Using an Unmanned Aerial Vehicle (UAV) Collected High Density Structure from Motion Point Cloud", Remote Sensing, 5(5), pp.2164~2183 (2013), MDPI AG[DOI]
  27. Francisco-Javier Mesas-Carrascosa, "Classification of 3D Point Clouds Using Color Vegetation Indices for Precision Viticulture and Digitizing Applications", Remote Sensing, 12(2), pp.317~ (2020), MDPI AG[DOI]
  28. "Agricultural business registration information inquiry site" (2021)[URL]
  29. Fatma Susilawati Mohamad, "Age prediction on face features via multiple classifiers", 2018 4th International Conference on Computer and Technology Applications (ICCTA), pp.161~166 (2018), IEEE
  30. Anders Krogh Mortensen, "Segmentation of lettuce in coloured 3D point clouds for fresh weight estimation", Computers and Electronics in Agriculture, 154, pp.373~381 (2018), Elsevier BV[DOI]
  31. 나상일, "드론 기반 초분광 영상을 이용한 배추 단수 추정의 최적밴드 선정", 대한원격탐사학회지, 35(3), pp.375~387 (2019), 대한원격탐사학회[DOI]
  32. Yue Pan, "3D Reconstruction of Ground Crops Based on Airborne LiDAR Technology", IFAC-PapersOnLine, 52(24), pp.35~40 (2019), Elsevier BV[DOI]
  33. 박진기, "농업분야 무인항공기 영상 활용 동향: 리뷰 및 제안", Korean Journal of Agricultural Science, 42(3), pp.269~276 (2015), 농업과학연구소
  34. Weiqiang Pi, "3D-CNN based UAV hyperspectral imagery for grassland degradation indicator ground object classification research", Ecological Informatics, 62, pp.101278~ (2021), Elsevier BV[DOI]
  35. "2021", ~
  36. Ricardo Sarabia, "Automated Identification of Crop Tree Crowns from UAV Multispectral Imagery by Means of Morphological Image Analysis", Remote Sensing, 12(5), pp.748~ (2020), MDPI AG[DOI]
  37. Julien Sarron, "Mango Yield Mapping at the Orchard Scale Based on Tree Structure and Land Cover Assessed by UAV", Remote Sensing, 10(12), pp.1900~ (2018), MDPI AG[DOI]
  38. M.W. Smith, "Structure from motion photogrammetry in physical geography", Progress in Physical Geography: Earth and Environment, 40(2), pp.247~275 (2015), SAGE Publications[DOI]
  39. Martinus Edwin Tjahjadi, "Fast and stable direct relative orientation of UAV-based stereo pair", International Journal of Advances in Intelligent Informatics, 5(1), pp.24~ (2019), Universitas Ahmad Dahlan, Kampus 3[DOI]
  40. Jorge Torres-Sánchez, "Mapping the 3D structure of almond trees using UAV acquired photogrammetric point clouds and object-based image analysis", Biosystems Engineering, 176, pp.172~184 (2018), Elsevier BV[DOI]
  41. Xu, Z., "A 3D convolutional neural network method for land cover classification using LiDAR and multi-temporal Landsat imagery", ISPRS Journal of Photogrammetry and Remote Sensing, 144(6), pp.423~434 (2018)[DOI]
  42. Si Yang, "An Efficient Processing Approach for Colored Point Cloud-Based High-Throughput Seedling Phenotyping", Remote Sensing, 12(10), pp.1540~ (2020), MDPI AG[DOI]
  43. Chunlong Zhang, "A method for organs classification and fruit counting on pomegranate trees based on multi-features fusion and support vector machine by 3D point cloud", Scientia Horticulturae, 278, pp.109791~ (2021), Elsevier BV[DOI]
  44. "2018", ~
  45. Ziliani, M. G., "Intra-season crop height variability at commercial farm scales using a fixed-wing UAV", Remote Sensing, 10(12), pp.2007~ (2018)[DOI]

관련 논문AI추천

무인기 기반 영상과 SVM 모델을 이용한 가을수확 작물 분류 - 충북 괴산군 이담리 지역을 중심으로 -고승환, 박종화, 정찬희한국농촌계획학회 · 농촌계획2022 · 제28권 제1호드론 영상 기반 노지 콩 품종 분류를 위한 딥러닝 모델의 적용 및 평가박 재성, 김설민, 박진기, 송철민, 안치용한국농공학회 · 한국농공학회논문집2025 · 제67권 제6호무인비행기 (UAV) 영상을 이용한 농작물 분류박종화, 박진기한국농공학회 · 한국농공학회논문집2015 · 제57권 제6호DeepLabv3+를 활용한 논콩 재배면적 분류 기술 개발강태안, 박진기, 송철민, 안치용한국농공학회 · 한국농공학회논문집2024 · 제66권 제6호색상지수 기반의 식물분할을 위한 다층퍼셉트론 신경망이문규한국산업경영시스템학회 · 한국산업경영시스템학회지2020 · 제43권 제1호Improved Plant Image Segmentation Method using Vegetation Indices and Automatic Thresholds강예성, 김성헌, 류찬석, 민영봉농업생명과학연구원 · 농업생명과학연구2015 · 제49권 제5호

이 간행물의 다른 논문 (8건)

BES를 사용한 에너지 절감형 양돈장의 지열히트펌프 적정용량 산정박광우, 이성원, 오병욱, 서일환pp. 1-13SWMM을 활용한 농업용수 네트워크 모형 단순화 분석- 만대 저수지 사례를 중심으로 -남원호, 김한중, 이종서, 안성수, 방나경, 방성수pp. 27-37CMIP5 기반 하천유량 예측을 위한 딥러닝 LSTM 모형의 최적 학습기간 산정김상우, 임경재, 신용철, 정영훈, 천범석, 도종원, 이태화pp. 39-50Sentinel-2 위성영상을 이용한 하계 논벼와 동계작물재배 필지 분류 및 정확도 평가송인홍, 홍주표, 신형진, 박진석, 장성주pp. 51-63만대·가아·자운지구 비점오염 유출특성 분석 및 저감사업 평가신민환, 우수민, 금동혁, 임경재, 홍은미pp. 65-77
원문 보기