농촌계획 (Journal of Korean Society of Rural Planning)

  • 제28권2호
  • /
  • Pages.87-96
  • /
  • 2022
  • /
  • 1225-8857(pISSN)
  • /
  • 2288-9493(eISSN)
한국농촌계획학회 (Korean Society of Rural Planning)
권호 표지
DOI QR코드

DOI QR Code

YOLO v2를 이용한 고해상도 항공영상에서의 태양광발전소 탐지 방법 연구

A Study on the Detection of Solar Power Plant for High-Resolution Aerial Imagery Using YOLO v2

  • 김하영 (전남대학교 농업생명과학대학 지역.바이오시스템공학과 BK21) ;
  • 나라 (전남대학교 농업생명과학대학 지역.바이오시스템공학과 BK21) ;
  • 주동혁 (전남대학교 농업생명과학대학 지역.바이오시스템공학과 BK21) ;
  • 최규훈 (위디비 주식회사) ;
  • 오윤경 (전남대학교 농업생명과학대학 농업과학기술연구소)
  • Kim, Hayoung (Department of Rural and Biosystems Engineering & BK21 Education and Research Unit for Climate-smart Reclaimed-Tideland Agriculture, Chonnam National University) ;
  • Na, Ra (Department of Rural and Biosystems Engineering & BK21 Education and Research Unit for Climate-smart Reclaimed-Tideland Agriculture, Chonnam National University) ;
  • Joo, Donghyuk (Department of Rural and Biosystems Engineering & BK21 Education and Research Unit for Climate-smart Reclaimed-Tideland Agriculture, Chonnam National University) ;
  • Choi, Gyuhoon (WeDB) ;
  • Oh, Yun-Gyeong (Institute of Agricultural Science & Technology, Chonnam National University)
  • 투고 : 2022.05.17
  • 심사 : 2022.05.30
  • 발행 : 2022.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

As part of strengthening energy security and responding to climate change, the government has promoted various renewable energy measures to increase the development of renewable energy facilities. As a result, small-scale solar installations in rural areas have increased rapidly. The number of complaints from local residents is increasing. Therefore, in this study, deep learning technology is applied to high-resolution aerial images on the internet to detect solar power plants installed in rural areas to determine whether or not solar power plants are installed. Specifically, I examined the solar facility detector generated by training the YOLO(You Only Look Once) v2 object detector and looked at its usability. As a result, about 800 pieces of training data showed a high object detection rate of 93%. By constructing such an object detection model, it is expected that it can be utilized for land use monitoring in rural areas, and it can be utilized as a spatial data construction plan for rural areas using technology for detecting small-scale agricultural facilities.

키워드

과제정보

2020년도 정부(과학기술정보통신부)의 재원으로 한국연구재단-중견연구사업의 지원을 받아 수행된 연구임(NRF-2020R1A2C1010502).

참고문헌

  1. Akihiko Ishikawa, 2020, Deep Learning Textbook to Learn using Python, Hanbit media. (in Korean)
  2. Al-Mashhadani, R., Alkawsi, G., Baashar, Y., Ahmed Alkahtani, A., Hani Nordin, F., Hashim, W. 2021, Deep learning methods for solar fault detection and classification: A review. Information Sciences Letters, 10(2): 13.
  3. Chin K., 2021, Problem Analysis and Improvement Measures of Rural Area Development for PV Power Plant Project, KIEAE Journal, 21(5): 83-90. (in Korean) https://doi.org/10.12813/kieae.2021.21.5.083
  4. Chuncheongbuk-do, 2021, Solar Power Project Permit Status, https://www.data.go.kr/ [accessed: March 5, 2022]
  5. Chungcheongnam-do, 2021, Solar Power Project Permit Status, https://www.data.go.kr/ [accessed: March 5, 2022]
  6. Electric Power Statistics Information System (EPSIS), 2021, Generation capacity by fuel, http://epsis.kpx.or.kr (in Korean)
  7. Golovko, V., Kroshchanka, A., Bezobrazov, S., Sachenko, A., Komar, M., & Novosad, O., 2018, Development of solar panels detector. In 2018 International Scientific- Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T) (pp. 761-764). IEEE.
  8. Gorlapraveen123, 2021, https://commons.wikimedia.org/wiki/File:ResNet50.png [accessed: May 10, 2022]
  9. Ha, J., Lee, S., Kim, D., 2022, Social media posts and user comment analysis on rural solar issues. Journal of The Korean Data Analysis Society (JKDAS), 24(2): 683-699. https://doi.org/10.37727/jkdas.2022.24.2.683
  10. Han, S. H., Rahim, T., Park J.. H., Shi, S. Y., 2020, Damaged solar panel detection drone system using deep learning and thermal imaging camera, Conference proceeding of The Korean Institute of Communications and Information Sciences. (in Korean)
  11. Jeollabuk-do, 2019, Solar Power Project Permit Status, https://www.data.go.kr/ [accessed: March 5, 2022]
  12. Jeollanam-do, 2018, Solar Power Project Permit Status, https://www.data.go.kr/ [accessed: April 15, 2020]
  13. Jo, W., Lim, Y., Park, K.-H., 2019, Deep learning based land cover classification using convolutional neural network:a case study of Korea, Journal of the Korean geographical society, 54(1): 1-16. (in Korean)
  14. Kakao-skyview, http://map.kakao.com [accessed: March 7~March 21, 2022]
  15. Kim, J. S. and Hong, I. Y., 2021, Analysis of Building Object Detection Based on the YOLO Neural Network Using UAV Images, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 39(6): 381-392. (in Korean) https://doi.org/10.7848/KSGPC.2021.39.6.381
  16. Korea Rural Economic Institute (KREI), 2018, Research on problems and improvement plans for the spread of rural solar power, KREI Report. (in Korean)
  17. Lee, S. and Kim, J., 2019, Land Cover Classification using Sematic Image Segmentation with Deep Learning, Korean Journal of Remote Sensing, 35(2): 279-288. (in Korean) https://doi.org/10.7780/KJRS.2019.35.2.7
  18. MathworksⒸ, http://kr.mathworks.com [accessed: April 7, 2022]
  19. Park, M.-L., Shin, S.-W., Oh, Si.-D., Kang, S.-H., 2019, Survey and Analysis of Resident Acceptability for Photovoltaic System in Rural Region- Focusing on Economic Factors, Conference proceeding of the Korean solar energy society, 198.
  20. Perez, R. M., Arias, J. S., Mendez-Porras, A. 2019, Solar panels recognition based on machine learning. In 2019 IV Jornadas Costarricenses de Investigacion en Computacion e Informatica (JoCICI) 1-5. IEEE.
  21. Planche, B. and Andres, E., 2020, Practice! Deep Learning Computer Vision with TensorFlow 2, Wikibooks. (in Korean)
  22. SaGong, J. H., Jung, O. S., Kwon, O. S., 2018, Current status of solar power generation facilities in Chungnam and ecological and landscape response strategies, Chungnam Report, 295, 1-13. (in Korean).