DOI QR코드

DOI QR Code

Automatic selection method of ROI(region of interest) using land cover spatial data

토지피복 공간정보를 활용한 자동 훈련지역 선택 기법

  • Received : 2018.09.25
  • Accepted : 2018.11.22
  • Published : 2018.12.10

Abstract

Despite the rapid expansion of satellite images supply, the application of imagery is often restricted due to unautomated image processing. This paper presents the automated process for the selection of training areas which are essential to conducting supervised image classification. The training areas were selected based on the prior and cover information. After the selection, the training data were used to classify land cover in an urban area with the latest image and the classification accuracy was valuated. The automatic selection of training area was processed with following steps, 1) to redraw inner areas of prior land cover polygon with negative buffer (-15m) 2) to select the polygons with proper size of area ($2,000{\sim}200,000m^2$) 3) to calculate the mean and standard deviation of reflectance and NDVI of the polygons 4) to select the polygons having characteristic mean value of each land cover type with minimum standard deviation. The supervised image classification was conducted using the automatically selected training data with Sentinel-2 images in 2017. The accuracy of land cover classification was 86.9% ($\hat{K}=0.81$). The result shows that the process of automatic selection is effective in image processing and able to contribute to solving the bottleneck in the application of imagery.

급속한 위성영상 공급확대에도 불구하고 자동화되지 못한 영상처리과정으로 인해 영상활용이 제약받는 경우가 많다. 본 연구에서는 감독영상분류를 위한 훈련지역 선택과정을 자동화함으로써 영상처리과정의 비용과 시간을 절감하는 방안을 제시하였다. 이를 위해 기존의 토지피복 정보를 활용하여 훈련관심영역을 추출하는 방법을 최신영상에 적용하여 토지피복분류를 실행한 후 분류정확도를 평가하였다. 원주시 도심지역을 대상지로 하여 토지유형을 시가지역과 농지/초지, 숲, 나대지 및 수계로 나누고 유형별 훈련관심영역을 환경부 중분류 토지피복지도를 활용하여 선택하였다. 관심영역 선택을 위해 먼저 토지피복지도 폴리곤 경계를 기준으로 negative buffer (-15m)를 적용하여 새로 폴리곤을 만들었고 너무 작은 폴리곤(<$2,000m^3$)과 큰 폴리곤(>$200,000m^3$)을 제외하였다. 선택된 폴리곤들의 밴드별 반사율 표준편차와 평균값 및 NDVI의 평균값을 계산하였다. 이 정보를 이용하여 먼저 표준편차가 적은 폴리곤 (폴리곤 내 반사율 값의 편차가 크지 않은 폴리곤)을 선택한 후 이들 중 반사율 평균값이 각 유형의 특징적인 분광특성을 반영할 수 있는 폴리곤을 관심영역으로 선택하였다. 2017년 Sentinel-2영상을 활용하여 토지피복유형을 분류한 결과 86.9%의 분류정확도($\hat{K}=0.81$)가 도출되었다. 본 연구에서 시도된 자동 관심영역 선택방법 적용한 결과 수동 디지타이징 과정을 생략하고도 높은 분류정확도를 도출 할 수 있었으며 이와 같은 방법을 통해 영상처리에 필요한 시간과 비용을 절약하여 급속히 증가하고 있는 영상을 효율적으로 활용할 수 있게 될 것으로 기대된다.

Keywords

References

  1. Alex Z. 2016. glcm: Calculate Textures from Grey-Level Co-Occurrence Matrices (GLCMs). R package version 1.6.1. https://CRAN.Rproject.org/package=glcm
  2. Breiman L. 2001. Random forest. Machine Learning. 45(1):5-32. https://doi.org/10.1023/A:1010933404324
  3. Beijma SV, Comber A, Lamb A. 2014. Random forest classification of salt marsh vegetation habitats using quad-polarimetric airborne SAR, elevation and optical RS data. Remote Sens. Environ. 149(1):118-129.
  4. Beon M-S, Cho KH, Kim HO, Oh H-K, Jeong J-C. 2017. Mapping of vegetation using multitemporal downscaled satellite images of a reclaimed area in Saemangeum, Republic of Korea. Remote Sensing. 9(3):272; https://doi.org/10.3390/rs9030272
  5. Chavez PS, Jr. 1996. Image-based atmospheric corrections - revisited and improved. Photogrammetric Engineering & Remote Sensing 62(9):1025-1036.
  6. Concoran J, Knight J, Gallant A. 2013. Influence of multi-source and multi-temporal remotely sensed and ancillary data on the accuracy of random forest classification of wetlands in northern Minnesota. Remote Sens. 5(7):3212-3238 https://doi.org/10.3390/rs5073212
  7. Congedo L. 2016. Semi-Automatic Classification Plugin Documentation. DOI: http://dx.doi.org/10.13140/RG.2.2.29474.02242/1
  8. Congalton RG. 1991. A review of assessing the accuracy of classification of remotely sensed data. Remote Sensing of Environment. 37(1):35-46. https://doi.org/10.1016/0034-4257(91)90048-B
  9. Dale PM. 2005. Shadow analysis in high-resolution satellite imagery of urban areas. Photogrammetric Engineering & Remote Sensing 71(2):169-177 https://doi.org/10.14358/PERS.71.2.169
  10. Hengel T, Nussbaum M, Wright MN, Heuvelink GBM, Graler B. 2018. Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ 6:e5518 https://doi.org/10.7717/peerj.5518
  11. Huang X, Weng C, Lu Q, Feng T, Zhang L. 2015. Automatic Labelling and Selection of Training Samples for High-Resolution Remote Sensing Image Classification over Urban Areas. Remote Sensing. 7(12): 16024-16044; https://doi.org/10.3390/rs71215819
  12. Jiang D, Huang Y, Zhuang D, Zhu Y, Xu X, Ren H. 2012. A Simple Semi-Automatic Approach for Land Cover Classification from Multispectral Remote Sensing Imagery. PLoS ONE 7, e45889. https://doi.org/10.1371/journal.pone.0045889
  13. Leroux L, Congedo L, Bellon B, Gaetano R, Begue A. 2018. Land Cover Mapping Using Sentinel ‐2 Images and the Semi‐Automatic Classification Plugin: A Northern Burkina Faso Case Study. In QGIS and Applications in Agriculture and Forest (eds Baghdadi N, Mallet C, Zribi M). doi:10.1002/9781119457107.ch4
  14. Liaw A, Wiener M. 2002. Classification and regression by random. Forest. R News 2(3):18-22.
  15. Lopes ME. 2015. Measuring the algorithmic convergence of random forests via bootstrap extrapolation. Davis: Department of Statistics, University of California, 25.
  16. R Core Team. 2017. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing: Vienna, Austria. Available online: https://www.Rproject.Org
  17. Shao Y, Taff GN, Walsh SJ. 2011. Shadow detection and building-height estimation using IKONOS data. International Journal of Remote Sensing. 32(22):6929-6944. https://doi.org/10.1080/01431161.2010.517226