지적과 국토정보 (Journal of Cadastre & Land InformatiX)

  • 제53권1호
  • /
  • Pages.107-121
  • /
  • 2023
  • /
  • 2508-3384(pISSN)
  • /
  • 2508-3392(eISSN)
한국국토정보공사 공간정보연구원 (LX Spatial Information Research Institute)
권호 표지
DOI QR코드

DOI QR Code

고해상도 위성영상과 인공지능을 활용한 국토 변화탐지 및 모니터링 연구: 실증대상 지역인 정읍시를 중심으로

A Study on the Land Change Detection and Monitoring Using High-Resolution Satellite Images and Artificial Intelligence: A Case Study of Jeongeup City

  • 조나혜 (공간정보연구원) ;
  • 이정주 (경북대학교 과학기술실용화연구센터) ;
  • 김현덕 (공간정보연구원)
  • Cho, Nahye (LX Spatial Information Research Institute) ;
  • Lee, Jungjoo (KNU Science and Technology Commercialization Research Center) ;
  • Kim, Hyundeok (LX Spatial Information Research Institute)
  • 투고 : 2023.05.20
  • 심사 : 2023.06.21
  • 발행 : 2023.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

실시간으로 변하는 국토를 광범위하게 취득하고, 이를 빠르고 정확하게 파악하기 위해 최근 공개 된 고해상도 국토위성 영상자료와 인공지능(AI; Artificial Intelligence)을 활용하고자 한다. 기존 위성 영상에 비해 국토위성의 경우 분광 및 주기 해상도가 높아져, 국토의 변화상을 주기적으로 모니터링하는 데 보다 적합한 자료원이 되었다. 따라서 본 연구는 국토위성을 취득하여 국토 변화를 탐지하기 위한 객체 8종을 선정하고, 이에 대한 데이터 셋 구축 및 AI 모델을 적용하여 분석하고자 한다. 다양한 유형의 객체 8종을 탐지하기 위한 최적의 모델과 변수 조건들을 확인하기 위해 여러 실험을 수행하고, AI 기반의 영상분석을 기술적으로 검토해보고자 한다.

In order to acquire a wide range of land that changes in real time and quickly and accurately grasp it, we plan to utilize the recently released high-resolution S.Korea's satellite image data and artificial intelligence (AI). Compared to existing satellite images, the spectral and periodic resolutions of S.Korea's satellite are higher, making them a more suitable data source for periodically monitoring changes in land. Therefore, this study aims to acquire S.Korea's satellite, select 8 types of objects to detect land changes, construct data sets for them, and apply AI models to analyze them. In order to confirm the optimal model and variable conditions for detecting 8 types of objects of various types, several experiments are performed and AI-based image analysis is technically reviewed.

키워드

참고문헌

  1. Kim J, Song YH, Lee WK. (2021). Accuracy analysis of multi-series phenological landcover classification using U-Net-based deep learning model-Focusing on the Seoul, Republic of Korea-. Korean Journal of Remote Sensing, 37(3), 409-418.  https://doi.org/10.7780/KJRS.2021.37.3.4
  2. Kim JY, Kim EJ. (2019). Application of Eco-friendly Planning of Sinseo Innovation City in Daegu using the Analysis of Satellite Image and Field Survey. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 37(3), 143-156.  https://doi.org/10.7848/KSGPC.2019.37.3.143
  3. Ryu JH, Han JG, An HY, Na SI, Lee BM, Lee GD. (2022). Development of Chinese Cabbage Detection Algorithm Based on Drone Multi-spectral Image and Computer Vision Techniques. Korean Journal of Remote Sensing, 38(5), 535-543. 
  4. Park SC, Park YB, Jang SY, Kim TH. (2022). A Study on Evaluating the Possibility of Monitoring Ships of CAS500-1 Images Based on YOLO Algorithm: A Case Study of a Busan New Port and an Oakland Port in California. Korean Journal of Remote Sensing, 38(6), 1463-1478. https://doi.org/10.7780/KJRS.2022.38.6.1.35
  5. 서기환, 오창화, 김다윗, 이민영. (2018). 지속가능한 국토발전을 위한 토지이용변화 모니터링 방안 연구: 딥러닝 알고리즘 활용을 중심으로. 세종:국토연구원. 
  6. Song CW, Wahyu W, Jung JH, Hong SJ, Kim DH, Kang JH. (2020). Urban change detection for high-resolution satellite images using U-Net based on SPADE. Korean Journal of Remote Sensing, 36(6_2), 1579-1590. 
  7. Shin JI, Kim IJ, Hwang DH, Lee JM, Lim SH. (2017). Availability Analysis on Detection of Small Scale Gas Emission Facilities using Drone Imagery. Journal of Cadastre & Land InformatiX, 47(1), 213-223. 
  8. Oh CS, Lim IT. (2010). A Study on the Reform Measure of the Survey of Individual Public Land Price Using Aerial Photographs - Focused on the Gwangyang City -. Journal of Cadastre & Land InformatiX, 40(1), 147-161. 
  9. Yun KH, Song YS. (2017). Observation on the Shoreline Changes Using Digital Aerial Imagery for Bangamoeri Beaches. Korean Journal of Remote Sensing, 33(6), 971-980. 
  10. Lee SH, Lee MJ. (2021). A Study of Establishment and application Algorithm of Artificial Intelligence Training Data on Land use/cover Using Aerial Photograph and Satellite Images. Journal of Remote Sensing, 37(5), 871-884. 
  11. Lee JH, Ryu KH, Shin CJ, Jung WM. (2016). Bathymetry estimation using aerial imagery for shallow water region. Journal of The Korean Society of Hazard Mitigation, 16(5), 351-358. 
  12. Choi KA. (2021). A Coastal Garbage Monitoring System Using Drones and AI Technologies: Focusing on the Case of Jeju Province. Journal of The Korean Society for Geospatial Information Science, 29(4), 127-138.  https://doi.org/10.7319/kogsis.2021.29.4.127
  13. Choi JH, Kim JH. (2019). Spatial Information Data Construction and Data Mining Analysis for Topography Investigation of Land Characteristics. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 37(6), 507-516.  https://doi.org/10.7848/KSGPC.2019.37.6.507
  14. Geraeds, M., van Emmerik, T., de Vries, R., bin Ab Razak, M. S. (2019). Riverine plastic litter monitoring using unmanned aerial vehicles (UAVs). Remote Sensing, 11(17), 2045. 
  15. Honkavaara, E., Eskelinen, M.A., Polonen, I., Saari, H., Ojanen, H., Mannila, R., Holmlund, C., Hakala, T., Litkey, P., Rosnell, T., Viljanen, N., Pulkkanen, M. (2016). Remote Sensing of 3-D Geometry and Surface Moisture of a Peat Production Area Using Hyperspectral Frame Cameras in Visible to Short-Wave Infrared Spectral Ranges Onboard a Small Unmanned Airborne Vehicle (UAV). IEEE Transactions on Geoscience and Remote Sensing, 54(9), 5440-5454.  https://doi.org/10.1109/TGRS.2016.2565471
  16. Lin, Z., Liu, H. H., Wotton, M. (2018). Kalman filter-based large-scale wildfire monitoring with a system of UAVs. IEEE Transactions on Industrial Electronics, 66(1), 606-615.  https://doi.org/10.1109/TIE.2018.2823658
  17. Martinez-de Dios, J. R., Merino, L., Caballero, F., Ollero, A. (2011). Automatic forest-fire measuring using ground stations and unmanned aerial systems. Sensors, 11(6), 6328-6353.  https://doi.org/10.3390/s110606328
  18. Moriya, E.A.S., Imai, N.N., Tommaselli, A.M.G., Miyoshi, G.T. (2017). Mapping Mosaic Virus in Sugarcane Based on Hyperspectral Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(2), 740-748.  https://doi.org/10.1109/JSTARS.2016.2635482
  19. Turner, D., Lucieer, A., De Jong, S. M. (2015). Time series analysis of landslide dynamics using an unmanned aerial vehicle (UAV). Remote Sensing, 7(2), 1736-1757.  https://doi.org/10.3390/rs70201736
  20. Youme, O., Bayet, T., Dembele, J. M., Cambier, C. (2021). Deep learning and remote sensing: detection of dumping waste using UAV. Procedia Computer Science, 185, 361-369.  https://doi.org/10.1016/j.procs.2021.05.037
  21. Zhang, Y., Xu, Y., Xiong, W., Qu, R., Ten, J., Lou, Q., Lv, N. (2021). Inversion study of heavy metals in soils of potentially polluted sites based on UAV hyperspectral data and machine learning algorithms. In 2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, (1-5). IEEE. 
  22. 국토지리정보원. 2023. 국토플랫폼 [인터넷]. [http://map.ngii.go.kr/ms/map/nlipCASImgMap.do]. 2023년 6월 4일 검색. 
  23. (NGII) National Geographic Information Institute. 2023. National Land Platform [Internet]. [http://map.ngii.go.kr/ms/map/nlipCASImgMap.do]. Last accessed 4 June 2023.