Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Water body extraction in SAR image using water body texture index

  • Ye, Chul-Soo (Department of Ubiquitous IT, Far East University)
  • Received : 2015.07.29
  • Accepted : 2015.08.18
  • Published : 2015.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Water body extraction based on backscatter information is an essential process to analyze floodaffected areas from Synthetic Aperture Radar (SAR) image. Water body in SAR image tends to have low backscatter values due to homogeneous surface of water, while non-water body has higher backscatter values than water body. Non-water body, however, may also have low backscatter values in high resolution SAR image such as Kompsat-5 image, depending on surface characteristic of the ground. The objective of this paper is to present a method to increase backscatter contrast between water body and non-water body and also to remove efficiently misclassified pixels beyond true water body area. We create an entropy image using a Gray Level Co-occurrence Matrix (GLCM) and classify the entropy image into water body and non-water body pixels by thresholding of the entropy image. In order to reduce the effect of threshold value, we also propose Water Body Texture Index (WBTI), which measures simultaneously the occurrence of repeated water body pixel pair and the uniformity of water body in the binary entropy image. The proposed method produced high overall accuracy of 99.00% and Kappa coefficient of 90.38% in water body extraction using Kompsat-5 image. The accuracy analysis indicates that the proposed WBTI method is less affected by the choice of threshold value and successfully maintains high overall accuracy and Kappa coefficient in wide threshold range.

Keywords

References

  1. Haralick, R.M., K. Shanmugam, and I. Dinstein, 1973. Texture features for image classification, IEEE Transaction on Systems, Man, and Cybernetics, 3(6): 610-621. https://doi.org/10.1109/TSMC.1973.4309314
  2. Kittler, J. and J. Illingworth, 1986. Minimum error thresholding, Pattern Recognition, 19: 41-47. https://doi.org/10.1016/0031-3203(86)90030-0
  3. Klemenjak, S., B. Waske, S. Valero, and J. Chanussot, 2012. Automatic detection of rivers in highresolution SAR data, Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(5): 1364-1372. https://doi.org/10.1109/JSTARS.2012.2189099
  4. Kuenzer, C., G. Huadong, J. Huth, P. Leinenkugel, L. Xinwu, and S. Dech, 2013. Flood mapping and flood dynamics of the mekong delta:ENVISAT-ASAR-WSM based time series analyses, Remote Sensing, 5: 687-715. https://doi.org/10.3390/rs5020687
  5. Martinis, S., J. Kersten, and A. Twele, 2015. A fully automated TerraSAR-X based flood service, ISPRS Journal of Photogrammetry and Remote Sensing, 104: 203-212. https://doi.org/10.1016/j.isprsjprs.2014.07.014
  6. Matgen, P., R. Hostache, G. Schumann b, L. Pfister, L. Hoffmann, and H.H.G. Savenije, 2011. Towards an automated SAR-based flood monitoring system: Lessons learned from two case studies, Physics and Chemistry of the Earth, 36: 241-252. https://doi.org/10.1016/j.pce.2010.12.009

Cited by

  1. Water body extraction using block-based image partitioning and extension of water body boundaries vol.32, pp.5, 2016, https://doi.org/10.7780/kjrs.2016.32.5.6
  2. 토픽모델링을 이용한 대한원격탐사학회지의 연구주제 분류 및 연구동향 분석: 자연·환경재해 분야를 중심으로 vol.37, pp.6, 2021, https://doi.org/10.7780/kjrs.2021.37.6.2.9