Journal of Cadastre & Land InformatiX (지적과 국토정보)

LX Spatial Information Research Institute (한국국토정보공사 공간정보연구원)
권호 표지
DOI QR코드

DOI QR Code

Accuracy evaluation of domestic and foreign land cover spectral libraries using hyperspectral image

초분광 영상을 활용한 국내외 토지피복 분광 라이브러리 정확도 평가

  • Park, Geun Ryeol (Department of Civil Engineering, Jeonbuk National University) ;
  • Lee, Geun-Sang (Department of Cadastre & Civil Engineering, Vision College of Jeonju) ;
  • Cho, Gi-Sung (Department of Civil Engineering, Jeonbuk National University)
  • 박근렬 (전북대학교 토목공학과) ;
  • 이근상 (전주비전대학교 지적토목학과) ;
  • 조기성 (전북대학교 토목공학과)
  • Received : 2021.09.27
  • Accepted : 2021.11.25
  • Published : 2021.12.10
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, land cover spectral libraries have been widely used in studies to classify land cover based on hyperspectral images. Overseas, various institutions have built and provided land cover spectral libraries, but in Korea, the building and provision of land cover spectral libraries is insufficient. Against this background, the purpose of this study is to suggest the possibility of using domestic and foreign spectral libraries in the classification studies of domestic land cover. Band matching is required for comparative analysis of the spectral libraries and land cover classification using the spectral libraries, and in this study, an automation logic to automatically perform this is presented. In addition, the directly constructed domestic land cover spectral library and the existing overseas land cover spectral library were comparatively analyzed. As a result, the directly constructed land cover spectral library had the highest correlation coefficient of 0.974. Finally, for the accuracy evaluation, aerial hyperspectral images of the study area were supervised and classified using the domestic and foreign land cover spectral libraries using the SAM technique. As a result of the accuracy evaluation, it is judged that Soils, Artificial Materials, and Coatings among the classification items of the foreign land cover spectral library can be sufficiently applied to classify the cover in Korea.

최근 초분광 영상을 기반으로 토지피복을 분류하는 연구에서 토지피복 분광 라이브러리가 많이 활용되고 있다. 해외에서는 다양한 기관에서 토지피복 분광 라이브러리를 구축 및 제공하고 있지만, 국내의 경우 토지피복 분광 라이브러리의 구축 및 제공이 부족한 실정이다. 이러한 배경에서 본 연구는 국내 토지피복의 분류 연구에서 국내외 분광 라이브러리의 활용 가능성을 제시하는데 목적이 있다. 분광 라이브러리의 비교분석 및 분광 라이브러리를 이용한 토지피복분류에는 밴드매칭이 요구되며, 본 연구에서는 이를 자동적으로 수행하기 위한 자동화 로직을 제시하였다. 또한 직접 구축한 국내 토지피복 분광 라이브러리와 기구축 해외 토지피복 분광 라이브러리를 비교분석하였으며, 그 결과 직접 구축한 토지피복 분광 라이브러리의 상관계수가 0.974로 가장 높게 나타났다. 최종적으로 정확도 평가를 위해 국내외 토지피복 분광 라이브러리를 이용하여 연구대상지역의 항공 초분광 영상을 SAM기법으로 감독분류 하였으며, 그 결과 직접 구축한 분광 라이브러리의 전체정확도가 91.78%로 가장 높게 나타났다. 정확도 평가 결과 해외 토지피복 분광 라이브러리의 분류항목 중 Soils, Artificial Materials, Coatings는 국내에서도 충분히 피복을 분류하는데 적용 가능할 것으로 판단된다.

Keywords

References

  1. Kim SW. 2007. Fundamentals Of Statics. Hakjisa. p. 97-99.
  2. Kim SH, Lee KS, Ma JL, Kook MJ. 2005. Current Status of Hyperspectral Remote Sensing: Principle, Data Processing Techniques, and Applications. Korean Journal of Remote Sensing. 21(4):341-369 https://doi.org/10.7780/KJRS.2005.21.4.341
  3. Kim YS. 2021. Analysis of Land Cover Change in the Waterfront Area of Taehwa River using Hyperspectral Image Information. Journal of the Korean Association of Geographic Information Studies. 24(1):11-12. https://doi.org/10.14352/jkaie.2020.24.1.11
  4. Park JS. 2016. Study on the spectral library establishing and availability for analysis of hyperspectral aviation image[Thesis]. Jeonbuk National University. p. 40-41.
  5. Park JS, Seo JJ, Go JW, Cho GS. 2016. The Study on Improving Accuracy of Land Cover Classification using Spectral Library of Hyperspectral Image. Journal of Cadastre & Land InformatiX. 46(2):240-243.
  6. Son YS, Lee BH, Kim NH, Koh SM. 2020. Mapping mineral distribution of outcrops in carbonate mines using ground-based hyperspectral imaging. Journal of the Geological Society of Korea. 56(6):753-754. https://doi.org/10.14770/jgsk.2020.56.6.753
  7. Sin JI, Kim SH, Lee KS. 2010. Design and Construction of Spectral Library for the Korean Peninsular. Korean Journal of Remote Sensing. 26(5):465-475. https://doi.org/10.7780/KJRS.2010.26.5.465
  8. Sim MS. 2014. Material Classification of Objects Using Hyperspectral images[Thesis]. Yeongnam University. p. 5-8.
  9. Yang JW. 2019. Building spectral library of SWIR hyperspectral image for improving the accuracy of land cover classification[Thesis]. Jeonbuk National University. p. 2-3.
  10. Lee JD, Bang KJ, Kim HH. 2018. Land Cover Classification of Coastal Area by SAM from Airborne Hyperspectral Images. Journal of the Korean Association of Geographic Information Studies. 21(1):35-36. https://doi.org/10.11108/KAGIS.2018.21.1.035
  11. Lim HH, Cheon E, Lee DH, Jeon JS, Lee SR. 2019. Soil Water Content Measurement Technology Using Hyperspectral Visible and Near-Infrared Imaging Technique. Journal of the Korean geotechnical society. 35(11):51-52.
  12. Jeong JC, Youn HJ. 2020. Region of Interest (ROI) Selection of Land Cover Using SVM Cross Validation. Journal of Cadastre & Land InformatiX. 50(1):75-76. https://doi.org/10.22640/LXSIRI.2020.50.1.75
  13. Cho KH, Jeong JC. 2018. Automatic selection method of ROI(region of interest) using land cover spatial data. Journal of Cadastre & Land InformatiX. 48(2):171-173. https://doi.org/10.22640/LXSIRI.2018.48.2.171
  14. Ha R, Lee H, Gang TG. 2014. Research trends and application prospects of hyperspectral sensor images. Journal of the Korean Society of Agricultural Engineers. 56(2):33-37.
  15. Boucher Y, Amiez A, Barillot P, Chatelard C, Coudrain C, Deliot P, Riviere N, Riviere T, Roupioz L. 2018. TERRISCOPE: An optical remote sensing research platform using aircraft and UAS for the characterization of continental surfaces. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences. 42(1):65-70.
  16. Hou Z, Li W, Tao R, Du Q. 2021. Three-Order Tucker Decomposition and Reconstruction Detector for Unsupervised Hyperspectral Change Detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 14:6194-6205. https://doi.org/10.1109/JSTARS.2021.3088438
  17. Kokaly RF, Clark RN, Swayze GA, Livo KE, Hoefen TM, Pearson NC, Klein AJ. 2017. USGS spectral library version 7 data: Us geological survey data release. United States Geological Survey (USGS): Reston, VA, USA. Data Series 1035-1.
  18. Laporte-Fauret Q, Lubac B, Castelle B, Michalet R, Marieu V, Bombrun L, Launeau P, Giraud M, Normandin C, Rosebery D. 2020. Classification of Atlantic Coastal Sand Dune Vegetation Using In Situ, UAV, and Airborne Hyperspectral Data. Remote Sensing. 12(14):1-25.
  19. Meerdink SK, Hook SJ, Roberts DA, Abbott EA. 2019. The ECOSTRESS spectral library version 1.0. Remote Sensing of Environment. 230(111196): 1-2.
  20. Padalia H, Pandey K, Arumugam RA. 2017. Development of a web-enabled spectral data archival, visualisation and analysis architecture for tropical phytodiversity inventory. Tropical Ecology. 58(2): 307-314.
  21. Peyghambari S, Zhang Y. 2021. Hyperspectral remote sensing in lithological mapping, mineral exploration, and environmental geology: an updated review. Journal of Applied Remote Sensing. 15(3):1-2.
  22. Yang J, Zhou A, Han L, Li Y, Xie Y. 2021. Monitoring urban black-odorous water by using hyperspectral data and machine learning. Environmental Pollution. 269(116166): 1-3.
  23. Zhu D, Du B, Zhang L. 2019. Target dictionary construction-based sparse representation hyperspectral target detection methods. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 12(4): 1254-1264. https://doi.org/10.1109/jstars.2019.2902430