Korean Journal of Remote Sensing (대한원격탐사학회지)

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

DOI QR Code

Water body extraction using block-based image partitioning and extension of water body boundaries

블록 기반의 영상 분할과 수계 경계의 확장을 이용한 수계 검출

  • Ye, Chul-Soo (Department of Aviation and IT Convergence, Far East University)
  • 예철수 (극동대학교 항공IT융합학과)
  • Received : 2016.10.05
  • Accepted : 2016.10.21
  • Published : 2016.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents an extraction method for water body which uses block-based image partitioning and extension of water body boundaries to improve the performance of supervised classification for water body extraction. The Mahalanobis distance image is created by computing the spectral information of Normalized Difference Water Index (NDWI) and Near Infrared (NIR) band images over a training site within the water body in order to extract an initial water body area. To reduce the effect of noise contained in the Mahalanobis distance image, we apply mean curvature diffusion to the image, which controls diffusion coefficients based on connectivity strength between adjacent pixels and then extract the initial water body area. After partitioning the extracted water body image into the non-overlapping blocks of same size, we update the water body area using the information of water body belonging to water body boundaries. The update is performed repeatedly under the condition that the statistical distance between water body area belonging to water body boundaries and the training site is not greater than a threshold value. The accuracy assessment of the proposed algorithm was tested using KOMPSAT-2 images for the various block sizes between $11{\times}11$ and $19{\times}19$. The overall accuracy and Kappa coefficient of the algorithm varied from 99.47% to 99.53% and from 95.07% to 95.80%, respectively.

본 논문에서는 수계 영역의 감독 분류 성능을 향상시키기 위하여 블록 기반의 영상 분할과 수계 경계의 확장을 이용하는 수계 검출 방법을 제안한다. 초기 수계 영역을 추출하기 위하여 수계 훈련 지역의 Normalized Difference Water Index (NDWI) 및 Near Infrared (NIR) 밴드 영상의 분광 정보를 이용하여 Mahalanobis 거리 영상을 생성한다. Mahalanobis 거리 영상에 포함된 잡음 성분의 영향을 감소시키기 위해서 인접한 화소의 연결 강도에 의해 확산 계수가 제어되는 평균 곡률 확산을 적용한 후에 초기 수계 영역을 추출한다. 추출된 수계 영상을 같은 크기의 블록으로 분할한 후에 수계 경계에 속하는 수계 영역의 정보를 이용하여 수계 영역을 갱신한다. 수계 경계에 속하는 수계 영역과 수계 훈련 지역 사이의 통계적인 거리가 임계값 이하이면, 수계 영역 갱신을 반복적으로 수행한다. 제안한 알고리즘을 KOMPSAT-2 영상에 적용한 결과 블록 크기가 $11{\times}11$에서 $19{\times}19$사이인 경우에 overall accuracy는 99.47%에서 99.53%, Kappa coefficient는 95.07%에서 95.80%의 분류 정확도를 보였다.

Keywords

References

  1. Kim, H.J., Y. Kim, and B. Lee, 2015. A study on the feature extraction using spectral indices from WorldView-2 satellite image, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 33(5):363-371. https://doi.org/10.7848/ksgpc.2015.33.5.363
  2. Kuenzer, C., G. Huadong, J. Huth, P. Leinenkugel, L. Xinwu, S. Dech, 2013. Flood mapping and flood dynamics of the mekong delta: ENVISATASAR-WSM based time series analyses, Remote Sensing, 5: 687-715. https://doi.org/10.3390/rs5020687
  3. 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
  4. Mcfeeters, S.K., 1996. The use of normalized difference water index (NDWI) in the delineation of open water features, International Journal of Remote Sensing, 17(7): 1425-1432. https://doi.org/10.1080/01431169608948714
  5. Xu, H., 2006. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery, International Journal of Remote Sensing, 27(4): 3025-3033. https://doi.org/10.1080/01431160600589179
  6. Yang, Y., Y. Liu, M. Zhou, S. Zhang, W. Zhan, C. Sun, and Y. Duan, 2015. Landsat 8 OLI image based terrestrial water extraction from heterogeneous backgrounds using a reflectance homogenization approach, Remote Sensing of Environment, 171: 14-32. https://doi.org/10.1016/j.rse.2015.10.005
  7. Ye, C.S., 2015a. Extraction of water body in before and after images of flood using Mahalanobis distance-based spectral analysis, Korean Journal of Remote Sensing, 31(4): 293-302. https://doi.org/10.7780/kjrs.2015.31.4.2
  8. Ye, C.S., 2015b. Water body extraction in SAR image using water body texture index, Korean Journal of Remote Sensing, 31(4): 337-346. https://doi.org/10.7780/kjrs.2015.31.4.6
  9. Ye, C.S., 2015c. A de-noising method based on connectivity strength between two adjacent pixels, Korean Journal of Remote Sensing, 31(1): 21-28. https://doi.org/10.7780/kjrs.2015.31.1.3
  10. Zhang, F., T. Tiyip, H. Kung, V.C. Johnson, J. Wang, and I. Nurmemet, 2016. Improved water extraction using Landsat TM/ETM+ images in Ebinur Lake, Xinjiang, China, Remote Sensing Applications: Society and Environment, 4: 109-118. https://doi.org/10.1016/j.rsase.2016.08.001
  11. Zhou, Y., J. Luo, Z. Shen, X. Hu, and H. Yang, 2014. Multiscale water body extraction in urban environments from satellite images, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(10): 4301-4312. https://doi.org/10.1109/JSTARS.2014.2360436

Cited by

  1. A Study on the Subdivision of Water Body in Watersheds Classified by Remote Sensing vol.38, pp.2, 2016, https://doi.org/10.7848/ksgpc.2020.38.2.87