Journal of the Korean Geographical Society (대한지리학회지)

The Korean Geographical Society (대한지리학회)
권호 표지

Evaluating Distribution Trends of Classification Accuracy by Triangular Training Operator in SAR/VIR FCC : A Case Study of Songkhla Lake Basin in Thailand

SAR/VIR FCC에서 삼각 트레이닝 도구에 의한 분류정확도 분포추세 평가: 태국의 송클라 호수 유역을 사례로

  • Jung Sup Um (Department of Geography, Kyungpook National University)
  • Published : 2003.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This study mainly focuses on evaluating how the triangular training operator could improve classification accuracy in SAR(Synthetic Aperture Radar) and VIR FCC(Visible Infra-red, False Colour Composite). The techniques for the determination of the most informative SAR/VIR combinations in the triangular space diagram, as developed tv the author of the paper, are given and the results obtained are presented. The SAR alone, VIR alone and SAR/VIR FCC classification showed trends for gradual improvement of accuracy. Accuracy distribution pattern for individual classes could be explained closely related to SAR/VIR signature components in the process of the triangular synergistic training. Due to contribution of SAR signature in training samples, it was possible to isolate major terrain features such as cloud cover area and roughness target with acceptable spatial precision. It is anticipated that this research output could be used as a valuable reference for distribution trends of classification accuracy obtained by triangular channel space based training in synergistic application.

SAR와 VIR 영상을 디지털 환경에서 통합하여 상승효과를 도출하려는 응용은 아직까지도 탐색적인 연구수준에 머물러 있다. 본 연구는 SAR와 VIR을 통합한 영상에서 삼각 트레이닝 도구가 개별 클라스의 분류 정확도의 분포추세에 미치는 영향을 평가하는 데 주안점을 두고 있다. SAR 데이터와 VIR 데이터가 단일 시너지 영상을 제작하기 위해 통합되었다. 분류정확도의 향상과정이 SAR, VIR, SAR/VIR 통합영상에서 단계적으로 확실하게 도출되었다. 아울러 개별 클라스의 분류정확도가 FCC에 의거한 트레이닝 샘플의 신호(signature)값과 밀접한 상관성을 가지고 분포되는 것이 확인되었다. 한 예로 FCC에서 SAR 영상 신호(signature)의 기여 때문에 구름으로 덮힌 지역과 굴곡을 지닌 지상물체가 (VIR에서는 사실상 분류가 불가능하였던) 상당한 공간 정확도를 가지고 분류되었다. 본 연구가 SAR/VIR을 통합한 응용분야에서 분류정확도의 분포추세에 대한 정량화되고 객관적인 근거가 부재하여 직면하였던 한계를 극복할 수 있는 계기가 되어 향후 SAT/VIR 원격탐사에서 개별 클라스에 대해 확보할 수 있는 분류 정확도에 대한 중요한 참고자료가 될 수 있을 것으로 사료된다.

Keywords

References

  1. Photogrammetric Engineering and Remote Sensing v.66 no.3 Application of DEM data to Landsat image classification: evaluation in a tropical wet-dry landscape of Thailand Apisit,E.;Rajendra,P.S.
  2. Earth Observation Quarterly Complementary nature of SAR and optical data: a case study in the tropics Ascbacher,J.;Lichtenegger,J.
  3. Geocarto International v.5 no.3 Visual versus digital analysis for vegetation mapping: some examples in central Spain Chuvieco,E.;Vega,J.M. https://doi.org/10.1080/10106049009354265
  4. Remote Sensing of Environment v.37 no.1 A review of assessing the accuracy of classifications of remotely sensed Data Congalton,R.G. https://doi.org/10.1016/0034-4257(91)90048-B
  5. International Journal of Remote Sensing v.19 no.6 A comparison of the potential for using optical and SAR data for geological mapping in an arid region: the Atar site Deroin,J.P.E.;Simonin,M.A. https://doi.org/10.1080/014311698215630
  6. International Journal of Remote Sensing v.11 no.10 Assumptions implicit in remote sensing data acquisition and analysis Duggin,M.J.;Robinove,C.J. https://doi.org/10.1080/01431169008955124
  7. The Landsat Turtorial Workbook,U.S. Geolological Survey v.829 The accuracy of selected land use and land cover maps at scales of 1:250,000 and 1:100.000 Fitzpatric-Lins,K.
  8. IEEE Transactions on Geocience and Remote Sensing v.26 no.1 Registration of images with geometric distortions Goshtasby,A. https://doi.org/10.1109/36.3000
  9. International Journal of Remote Sensing v.17 no.1 DEM corrected ERS-1 SAR data for snow monitoring Guneriussen,T.;Johnsen,H.;Sand,K. https://doi.org/10.1080/01431169608948994
  10. Phogrammetric Engineering and Remote Sensing v.66 no.6 Radar and optical data integration for land-use/land-cover mapping Haack,B.N.;Herold,N.D.;Bechdol,M.A.
  11. International Journal of Remote Sensing v.21 no.3 Land cover discrimination from multi-temporal ERS images and multi-spectral Landsat images: a study case in an agricultrual area in France Hegarat-Mascle,S.L.;Quesney,A.;Vidal-Madjar,D.;Taconet,O.;Normand,M.;Loumagne,C. https://doi.org/10.1080/014311600210678
  12. International Journal of Remote Sensing v.18 no.7 The integration of optical and radar data to characterize mineralogy and morphology of surfaces in Death Valley Kierein-Young,K.S. https://doi.org/10.1080/014311697218250
  13. International Journal of Remote Sensing v.21 no.10 The study of ERS-1 SAR and Landsat TM synergism for land use classification Kuplich,T.M.;Freitas,C.C.;Soares,J.V. https://doi.org/10.1080/01431160050021321
  14. International Journal of Remote Sensing v.22 no.16 A generalized confusion matrix for assessing area estimates from remotely sensed data Lewis,H.G.;Brown,M. https://doi.org/10.1080/01431160152558332
  15. Photogrammetric Engineering and Remote Sensing v.64 no.12 The influence of geographic sampling methods on vegetation map accuracy evaluation in a swampy environment Lo,C.P.;Watson,L.J.
  16. Photogrammetric Engineering and Remote Sensing v.64 no.6 Accuracy assessment of a land-cover map of the Kuparuk river basin, Alaska: considerations for remote regions Muller,S.V.;Walker,D.A.;Nelson,F.E.;Auerback,N.A.;Bockheim,J.G.;Guyer,S.;Sherba,D.
  17. International Journal of Remote Sensing v.18 no.7 Airborne and spaceborne synthetic aperture radar (SAR) integration with Landsat TM and gamma ray spectrometry for geological mapping in a tropical rainforest envirnment Paradella,W.R.;Bignelli,P.A.;Veneziani,P.;Pietsch,R.W.;Tountin,T. https://doi.org/10.1080/014311697218232
  18. Photogrammetric Engineering and Remote Sensing v.66 no.4 Multispectral satellite image and ancillary data integration for geological calssification Richetti,E.
  19. International Journal of Remote Sensing v.22 no.11 Visible-infrared and radar imagery fusion for geological application: a new approach useing DEM and sun-illumination model Richetti,E.
  20. International Journal of Remote Sensing v.19 no.18 Multisource ERS-1 and optical data for vegetal cover assessment and monitoring in a semi-arid region of Algeria Smara,Y.A.;Belhadj-Aissa,B.;Sansal.J.;Lichtenegger,A.B. https://doi.org/10.1080/014311698213812
  21. International Institute for Aerospace Survey and Earth Science Investigation for setting a conceptual organization framework of the geo-information system for Songkhla basin development management Vintta,P.