Sentinel-2 위성영상을 이용한 하계 논벼와 동계작물재배 필지 분류 및 정확도 평가
Classification of Summer Paddy and Winter Cropping Fields Using Sentinel-2 Images
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Up-to-date statistics of crop cultivation status is essential for farm land management planning and the advancement in remote sensing technology allowsfor rapid update of farming information. The objective of this study was to develop a classification model of rice paddy or winter crop fields basedon NDWI, NDVI, and HSV indices using Sentinel-2 satellite images. The 18 locations in central Korea were selected as target areas and photographedonce for each during summer and winter with a eBee drone to identify ground truth crop cultivation. The NDWI was used to classify summer paddyfields, while the NDVI and HSV were used and compared in identification of winter crop cultivation areas. The summer paddy field classification withthe criteria of –0.195<NDWI<0.15 was 90.9% accurate on average when compared with ground truth. Model performance for the winter crop fieldclassification was also excellent showing the accuracy greater than 98.2% on average for both models. However, cloud and greenhouses appeared todemonstrate optical similarity with paddy in the NDWI values, implying additional caution should be taken when removing cloud and greenhouseeffects. Overall the developed methods for paddy and winter crop classification performed reasonably well at the irrigation district level and furtherstudies are needed to investigate model performance at regional or national scales.
Abstract
Up-to-date statistics of crop cultivation status is essential for farm land management planning and the advancement in remote sensing technology allowsfor rapid update of farming information. The objective of this study was to develop a classification model of rice paddy or winter crop fields basedon NDWI, NDVI, and HSV indices using Sentinel-2 satellite images. The 18 locations in central Korea were selected as target areas and photographedonce for each during summer and winter with a eBee drone to identify ground truth crop cultivation. The NDWI was used to classify summer paddyfields, while the NDVI and HSV were used and compared in identification of winter crop cultivation areas. The summer paddy field classification withthe criteria of –0.195<NDWI<0.15 was 90.9% accurate on average when compared with ground truth. Model performance for the winter crop fieldclassification was also excellent showing the accuracy greater than 98.2% on average for both models. However, cloud and greenhouses appeared todemonstrate optical similarity with paddy in the NDWI values, implying additional caution should be taken when removing cloud and greenhouseeffects. Overall the developed methods for paddy and winter crop classification performed reasonably well at the irrigation district level and furtherstudies are needed to investigate model performance at regional or national scales.
참고문헌 (30)
- Alex F. P., "Aplicación de técnicas de teledetección para apoyar el uso sostenible del agua en un contexto de cambio climático en la cuenca del río Barbate", Good stuffinternational (2019)
- 채수환, "노이즈에 강인한 HSV 색상 모델 기반손 윤곽 검출 시스템", 멀티미디어학회논문지, 18(10), pp.1149~1156 (2015), 한국멀티미디어학회[DOI]
- 최연웅, "HSI 컬러모델을 활용한 건물의 3차원 공간정보 추출시스템 개발", 대한공간정보학회지, 21(4), pp.151~159 (2013), 대한공간정보학회[DOI]
- Gao, B. C., "NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space", Remote Sensing of Environment, 58(3), pp.257~266 (1996)[DOI]
- Esmael Hamuda, "Automatic crop detection under field conditions using the HSV colour space and morphological operations", Computers and Electronics in Agriculture, 133, pp.97~107 (2017), Elsevier BV[DOI]
- 홍석영, "MODIS NDVI와 강수량 자료를 이용한 북한의 벼 수량 추정 연구", 대한원격탐사학회지, 31(5), pp.441~448 (2015), 대한원격탐사학회[DOI]
- Hong, S. Y., "Estimation of rice-planted area using Landsat TM imagery in Dangjin-gun area", NIAST, 3(1), pp.5~15 (2000)[DOI]
- Xinyu Hu, "Study on Classification Corn Seedling and Weed Based on RGB Model and HSV Model", Agriculture, Forestry and Fisheries, 6(1), pp.49~ (2017), Science Publishing Group[DOI]
- Alfredo R. Huete, "Vegetation Indices, Remote Sensing and Forest Monitoring", Geography Compass, 6(9), pp.513~532 (2012), Wiley[DOI]
- Anikó Kern, "Statistical modelling of crop yield in Central Europe using climate data and remote sensing vegetation indices", Agricultural and Forest Meteorology, 260-261, pp.300~320 (2018), Elsevier BV[DOI]
- 김준환, "경험적 벼 작황예측 방법에 대한 소개와 원격탐사를 이용한 예측과의 비교", 대한원격탐사학회지, 33(5), pp.733~740 (2017), 대한원격탐사학회
- 김강섭, "영상처리를 이용한 토마토 생육량 측정 시스템", 한국통신학회논문지, 45(8), pp.1460~1471 (2020), 한국통신학회[DOI]
- Development of yield estimation method for major crops using remote sensing technique, "KOSTAT", ~ (2011)
- 이대현, "영상기반 축사 내 육계 검출 및 밀집도 평가 연구", 한국정보전자통신기술학회 논문지, 12(4), pp.373~379 (2019), 한국정보전자통신기술학회
- 이희진, "Sentinel-2 위성영상을 활용한 농업용 저수지 가용수량 추정", 한국농공학회논문집, 62(6), pp.1~9 (2020), 한국농공학회[DOI]
- 이경도, "Sentinel-1 및 UAV 영상을 활용한 김제시 벼 재배 조기 추정", 대한원격탐사학회지, 37(3), pp.503~514 (2021), 대한원격탐사학회[DOI]
- Kyung-Do Lee, "Estimation of Rice Cultivation Area by Threshold Method using Sentinel-1 Imagery in South Korea", 한국토양비료학회지(Korean Journal of Soil Science and Fertilizer), 53(3), pp.345~354 (2020), 한국토양비료학회[DOI]
- 이수봉, "Landsat-8 위성영상을 이용한 수계면적 변화 탐지", 한국방재학회논문집, 17(3), pp.391~398 (2017), 한국방재학회[DOI]
- 이상현, "RapidEye 위성영상의 시계열 NDVI 및 객체기반 분류를 이용한 북한 재령군의 논벼 재배지역 추출 기법 연구", 한국농공학회논문집, 56(3), pp.55~64 (2014), 한국농공학회
- S. K. McFEETERS, "The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features", International Journal of Remote Sensing, 17(7), pp.1425~1432 (1996), Informa UK Limited[DOI]
- 나상일, "계층분류 기법을 이용한 위성영상 기반의 동계작물 구분도 작성", 대한원격탐사학회지, 33(5), pp.677~687 (2017), 대한원격탐사학회
- 나상일, "Mapping the Spatial Distribution of IRG Growth Based on UAV", 한국토양비료학회지(Korean Journal of Soil Science and Fertilizer), 49(5), pp.495~502 (2016), 한국토양비료학회[DOI]
- 나상일, "무인기 기반 RGB 영상을 이용한 동계작물 바이오매스 평가 모델 개발", 대한원격탐사학회지, 34(5), pp.709~720 (2018), 대한원격탐사학회[DOI]
- 나상일, "원격탐사 기반 맥류 작황 추정을 위한 최적 식생지수 선정 - UAV와 현장 측정자료를 활용하여 -", 대한원격탐사학회지, 32(5), pp.483~497 (2016), 대한원격탐사학회[DOI]
- Pandya, A., "Classification of vegetation area from satellite images using image processing techniques. International Journal of Research in IT", Management and Engineering, 5(3), pp.2249~1619 (2015)[DOI]
- 박진기, "무인항공기와 GIS를 이용한 논 가뭄 발생지역 분석", 한국농공학회논문집, 59(3), pp.21~28 (2017), 한국농공학회[DOI]
- 박진석, "드론영상을 활용한 논 유기물 관리 인자 조사 및 메탄가스 배출량 산정", 한국농공학회논문집, 62(3), pp.39~49 (2020), 한국농공학회[DOI]
- Jinru Xue, "Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications", Journal of Sensors, 2017, pp.1~17 (2017), Hindawi Limited[DOI]
- 유희영, "고해상도 다중시기 위성영상을 이용한 밭작물 분류: 마늘", 양파 재배지 사례연구, 2017, pp.33(5), 621~630[DOI]
- Weichun Zhang, "Mapping Rice Paddy Based on Machine Learning with Sentinel-2 Multi-Temporal Data: Model Comparison and Transferability", Remote Sensing, 12(10), pp.1620~ (2020), MDPI AG[DOI]