Korean Journal of Remote Sensing (대한원격탐사학회지)

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

DOI QR Code

Automated Landmark Extraction based on Matching and Robust Estimation with Geostationary Weather Satellite Images

정합과 강인추정 기법에 기반한 정지궤도 기상위성 영상에서의 자동 랜드마크 추출기법 연구

  • Lee Tae-Yoon (Department of Geoinformatic Engineering, Inha University) ;
  • Kim Taejung (Department of Geoinformatic Engineering, Inha University) ;
  • Choi Hae-Jin (Satellite Mission Operation Department, Korea Aerospace Research Institute)
  • 이태윤 (인하대학교 지리정보공학과) ;
  • 김태정 (인하대학교 지리정보공학과) ;
  • 최해진 (항공우주연구원 지상수신관제그룹)
  • Published : 2005.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

The Communications, Oceanography and Meteorology Satellite(COMS) will be launched in 2008. Ground processing for COMS includes the process of automatic image navigation. Image navigation requires landmark detection by matching COMS images against landmark chips. For automatic image navigation, a matching must be performed automatically However, if matching results contain errors, the accuracy of Image navigation deteriorates. To overcome this problem, we propose use of a robust estimation technique called Random Sample Consensus (RANSAC) to automatically detect erroneous matching. We tested GOES-9 satellite images with 30 landmark chips that were extracted from the world shoreline database. After matching, mismatch results were detected automatically by RANSAC. All mismatches were detected correctly by RANSAC with a threshold value of 2.5 pixels.

2008년도에 발사 예정인 통신해양기상위성은 자동 영상기반 항법을 수행할 예정이다. 자동 영상기반 항법을 위해서는 랜드마크 칩과 영상간의 정합을 수행하는 랜드마크 검출도 자동 수행되어야 한다. 그러기 위해서는 자동 정합의 문제점인 오정합에 대한 해결책이 필요하다. 이런 문제를 해결하기 위해서 우리는 강인추정기법 중 하나인 Random Sample Consensus (RANSAC)를 통한 자동 오정합 판별을 제안한다. 우리는 RANSAC을 이용한 자동 오정합 판별을 실험하기 위해서 GOES-9의 영상과 해안선 데이터베이스에서 추출한 30개의 랜드마크 칩을 이용하여 정합을 수행하였다. 정합수행 후에 RANSAC 추정 기법으로 오정합을 판별해 내었으며, RANSAC에 오차 임계값으로 2.5 픽셀을 설정했을 때, 모든 오정합을 판별할 수 있었다.

Keywords

References

  1. 김태정, 김승범, 신동석, 2000. 대표적 위성영상 카메라 모델링 알고리즘들의 비교연구, Journal of the Korean Society of Remote Sensing, 16(1): 73-86
  2. 이흥규 외, 1999. EOC 영상 자료 처리 및 활용 기술 개발 보고서, 한국과학기술원 인공위성연구센터
  3. Bass, J., P. Davies, and D., McCann, 2000. MTSAT Image Data Acquisition and Control System, Proc. Of the Conference 'DASIA 2000-Data systems in Aerospace', Montreal, Canada, May, 457: 509-514
  4. Chen, C-S., Y-P. Hung, and J-B. Cheng, 1999. RANSAC-Based DARCES: A new approach to fast automatic registration of partially overlapping range images, IEEE transactions Pattern Analysis and Machine Intelligence, 21(11): 1229-1234 https://doi.org/10.1109/34.809117
  5. Cheng, Y. C. and S. C. Lee, 1995. A new method for quadratic curve detection using K-RANSAC with acceleration techniques, Pattern Recognition, 28(5): 663-682 https://doi.org/10.1016/0031-3203(94)00138-C
  6. Emery, W. J., D. Baldwin, and D. Matthews, 2003. Maximum cross correlation automatic satellite image navigation and attitude corrections for open-ocean image navigation, IEEE transactions on geoscience and remote sensing, 41(1): 33-42 https://doi.org/10.1109/TGRS.2002.808061
  7. Emery, W. J., J. Brown, and Z. P. Nowak, 1989. AVHRR Image Navigation: Summary and Review, Photogrammetric Engineering and Remote Sensing, 55(8): 1175-1183
  8. Fischler, Martin A. and Robert C. Bolles, 1981. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Communications of the ACM, 24(6): 381-395 https://doi.org/10.1145/358669.358692
  9. Kamel, A. A, 1996. GOES Image Navigation and Registration System, Proc. Of SPIE Conference on GOES-8 and. Beyind, Denver, USA, AUGUST, 2812: 766-776
  10. Kelly, K. A and J. F. Hudson, 1996. GOES 8/9 Image Navigation and Registration Operations, Proc. Of SPIE Conference on GOES-8 and Beyind, 2812: 777-788
  11. Kim, T. and Y-J. Im, 2003. Automatic Satellite Image Registration by Combination of Stereo Matching and Random Sample Consensus, IEEE transactions on geoscience and remote sensing, 41(5): 1111-1117 https://doi.org/10.1109/TGRS.2003.811994
  12. McGuire, M. and H. S. Stone, 2000. Techinques for multiresolution image registration in the presence of occlusions, IEEE transactions on geoscience and remote sensing, 38(3): 1476-1479 https://doi.org/10.1109/36.843046
  13. NOAA/NESDIS, 1998, Earth Location User's Guide (ELUG), NOAA/SD3-1998-015R1 UD0, http:// rsd.gsfc.nasa.gov I goesl text/
  14. Space Systems-Loral, 1996. GOES DataBook, http://rsd.gsfc.nasa.gov/goes/
  15. Torr, P., R. Szeliski, and P. Anandan, 2001. An integratedBayesian approach to layer extraction from image sequences, IEEE transactions Pattern Analysis and Machine Intelligence, 23(3): 297-303 https://doi.org/10.1109/34.910882
  16. Wessel, P. and W. H. F. Smith, 1996. A global, self-consistent, hier-archical, high-resolution shoreline database, JOURNAL OF GEOPHYSICAL RESEARCH, 101 (B4): 8741-8743 https://doi.org/10.1029/96JB00104