대한원격탐사학회지 (Korean Journal of Remote Sensing)

  • 제14권4호
  • /
  • Pages.376-391
  • /
  • 1998
  • /
  • 1225-6161(pISSN)
  • /
  • 2287-9307(eISSN)
대한원격탐사학회 (Korean Society of Remote Sensing)
권호 표지
DOI QR코드

DOI QR Code

대용량 고해상 위성영상처리 시스템 개발

Development of an Image Processing System for the Large Size High Resolution Satellite Images

  • 김경옥 (한국전자통신연구원, 컴퓨터·소프트웨어기술연구소) ;
  • 양영규 (한국전자통신연구원, 컴퓨터·소프트웨어기술연구소) ;
  • 안충현 (한국전자통신연구원, 컴퓨터·소프트웨어기술연구소)
  • 발행 : 1998.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

위성의 발달에 따라 고해상영상이 등장하게 되었고 지표상태 분석에 매우 유용하게 되었다. GeoWatch는 지능형 영상처리 시스템으로서, 고해상도 영상을 이용하여 디지타이징, 지리보정, 강조, 여러 가지 연산, 식생지수 분석, 등을 하여 지표면 분석 등을 할 수 있는 시스템이다. 도한 지능형 분석 방법등 여러 가지 기법을 이용하여 변화지역분석, 토지 분류, 도시정보추출 등을 수행한다. 이 시스템의 강점은 full scene 영상같은 대용량 영상을 다룰 경우 역동적인 알고리즘 저장 방식을 채택하였고, 자동메뉴 생성, 사용자 편의를 위한 비쥬얼 프로그래밍 환경 등을 제공한다. 이 시스템은 또한 위성영상 위에 벡터를 중첩하여 분석하거나 수정 작업을 할 수 있고, 3차원 비행 시뮬레이션도 가능하다. 이 시스템은 영상 처리 모듈 외에도 영상 변환 및 수정 유틸리티 기능을 많이 제공한다. 본 논문에서는 또한 지능형 영상 분석 방법 뿐만 아니라, 대용량처리나, 비쥬얼 프로그램을 위한 디자인 개념을 제공한다.

Images from satellites will have 1 to 3 meter ground resolution and will be very useful for analyzing current status of earth surface. An image processing system named GeoWatch with more intelligent image processing algorithms has been designed and implemented to support the detailed analysis of the land surface using high-resolution satellite imagery. The GeoWatch is a valuable tool for satellite image processing such as digitizing, geometric correction using ground control points, interactive enhancement, various transforms, arithmetic operations, calculating vegetation indices. It can be used for investigating various facts such as the change detection, land cover classification, capacity estimation of the industrial complex, urban information extraction, etc. using more intelligent analysis method with a variety of visual techniques. The strong points of this system are flexible algorithm-save-method for efficient handling of large size images (e.g. full scenes), automatic menu generation and powerful visual programming environment. Most of the existing image processing systems use general graphic user interfaces. In this paper we adopted visual program language for remotely sensed image processing for its powerful programmability and ease of use. This system is an integrated raster/vector analysis system and equipped with many useful functions such as vector overlay, flight simulation, 3D display, and object modeling techniques, etc. In addition to the modules for image and digital signal processing, the system provides many other utilities such as a toolbox and an interactive image editor. This paper also presents several cases of image analysis methods with AI (Artificial Intelligent) technique and design concept for visual programming environment.

키워드

참고문헌

  1. Pattern Recognition v.25 no.1 Object Recognition Using Invariant Object Boundary Representations and Neural Network Models Bebis;George, N.;George, M.;Papadourakis
  2. IGARSS '94, California Institute of Technology Pasadena v.4 Multispectral Classification by a Modular Neural Network Architecture Blonda, P.;V. la forgia;Pasquariello;Satalino
  3. In Proc. Of Fourth International Conference on Interaction Information and Processing Systems for Meteorology Oceanography, and Hydrology A Next Generation MCIDAS Workstation Hibbard, William L.
  4. J. of Visual Languages and Computing 3 Visual languages and computing survey: daat flow visual programming languages Hils, D. D.
  5. 1990 IEEE Int'l Conf. on Systems Man and Cybernetics IDF: A Graphical Data Flow Programming Language for Image Processing and Computer Vision Hunt, N.
  6. Photogrammetric Engineering and Remote Sensing v.60 no.1 Segment-Based Land-Use Classicfication from SPOT Satellite Data Johnsson, Katarina
  7. IEEE Transactions on Patterns Analysis and Machine Intelligence v.12 no.5 Classification of Invariant by Zernike Moments Khotanzad, A;J. Lu
  8. SERI Journal v.1 no.1 Texture Classification Using Wavelet Frame and Neural Network Kim, K. O.;Y. K. Yang
  9. In Proc. of IEEE International Geoscience and Remote Sensing Symposium (IGARSS) '95, IEEE catalog #95CH35770 v.2 Classificationof Multispectral Image Using Neural Network Kim, K. O.;Y. K. Yang(et al.)
  10. In Proc. of World Congress of Neural Net(WCNN) '95, Washington D.C. Invariant Image Recognition Using Neural Network Kim, K. O.;Y. K. Yang(et al.)
  11. International Archives of Photogrammetry and Remote Sensing Shape Discrimination by Descriptors and Moments Using Neural Network Kim, K. O.;Y. K. Yang;Y. H. Park;T. K. Kim
  12. J. of Visual Languages and Computing 8 Criteria for evalution of visual programming languages Kiper, J. D.;E. Howard;C. Ames
  13. IEEE Transactions on Image Processisng v.3 no.3 The Khoros Software Development Environment for Image and Signal Processing Konstantinides K.
  14. IEEE Trans. Patt. Analysis and Machine Intell. v.11 no.7 Multi-resolutin Signal Decomposition: The Wavelet Representation Mallat, S.G.
  15. Computer Processing of Remotely-sensed Images Mather, P.M.
  16. Conference Processing, CHI'86:Human Factors in computing System Visual programming, programming by example and program visualization: a taxonomy Myers, B. A.
  17. Proceeding of ISPRS v.29 Multitemporal Remote Sensing Data Classification Using Neural Network Pasquariello, G.;P. Blonda
  18. IEEE Transaction on Neural Network v.1 no.1 Self-Organizing Network for Optimum Supervised Learning Tenorio, Manoel F.;Wei-Tshin Lee
  19. The Visual Computer 9 Components of the visual computer Singh, G.;M. H. Chignell
  20. IEEE Trans. On Image Processing v.4 no.11 Texture Classification and Segmentation Using Wavelet Frames Unser, M.
  21. IEEE Transaction on Geoscience and Remote Sensing v.32 no.5 Neural Network Approach to LandCover Mapping Yoshida, Tomoji;Sigeru Omatu