KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison of Image Matching Method for Automatic Matching of High Resolution SAR Imagery

SAR 영상 자동정합을 위한 영상정합기법의 비교연구

  • 백상호 (육군사관학교 건설환경학과) ;
  • 홍승환 (연세대학교 토목환경공학과) ;
  • 유수홍 (중앙항업(주) 지리정보연구소) ;
  • 손홍규 (연세대학교 토목환경공학과)
  • Received : 2014.05.30
  • Accepted : 2014.07.05
  • Published : 2014.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

SAR satellite can acquire clear imagery regardless of weather and the images are widely used for land management, natural hazard monitoring and many other applications. Automatic image matching technique is necessary for management of a huge amount of SAR data. Nevertheless, it is difficult to assure the accuracy of image matching due to the difference of image-capturing attitude and time. In this paper, we compared performances of MI method, FMT method and SIFT method by applying arbitrary displacement and rotation to TerraSAR-X images and changing resolution of the images. As a result, when the features having specific intensity were distributed well in SAR imagery, MI method could assure 0~2 pixels accuracy even if the images were captured in different geometry. But the accuracy of FMT method was significantly poor for the images having different spatial resolutions and the error was represented by tens or hundreds pixels. Moreover, the ratio of corresponding matching points for SIFT method was only 0~17% and it was difficult for SIFT method to apply to SAR images captured in different geometry.

SAR 센서는 마이크로파를 이용한 능동센서로 기상조건에 상관없이 영상을 취득할 수 있다는 장점이 있어, 국토관리 및 재해 모니터링 등에 활발히 활용되고 있다. 주기적으로 취득되는 SAR 영상을 효과적으로 활용하기 위해서는 자동화된 영상 정합기법이 필요하지만 영상의 촬영 시간 및 기하에 따라 다른 양상의 기하조건을 가진 취득됨에 따라 충분한 정합 정확도를 기대하기 어렵다. 이에 본 연구에서는 기울기 속성을 추가한 MI (Mutual Information) 기법과 FMT (Fourier-Mellin Transform)기법, SIFT (Scale-Invariant Feature Transform) 기법을 임의의 변위와 회전 공차를 적용하고, 해상도를 변화시킨 TerraSAR-X 영상에 적용하여 그 결과를 비교하였다. 비교 결과, MI 기법의 경우엔 서로 상이한 기하에서 촬영된 영상에 적용하였을 때에도 일정 크기의 영상소가 다수 분포할 경우 0~2 픽셀 수준의 정확도를 지닐 수 있는 반면, FMT 기법의 경우에는 같은 사물에 대해서도 그 영상소 값이 서로 상이하여 정합 오차가 수십에서 수백 픽셀로 나타났다. 또한 SIFT 기법의 경우에도 영상 정합을 위한 공액점의 정확도가 0~17 % 수준으로 매우 낮아 서로 상이한 기하조건으로 취득된 SAR 영상에 적용이 어려울 것으로 나타났다.

Keywords

References

  1. Abdelfattah, R. and Nicolas, J. M. (2005). "InSAR image coregistration using the Fourier-Mellin transform." International Journal of Remote Sensing, Vol. 26, No. 13, pp. 2865-2876. https://doi.org/10.1080/01431160512331338050
  2. Chen, H. M., Arora, M. K. and Varshney, P. K. (2003). "Mutual information-based image registration for remote sensing data." International Journal of Remote Sensing, Vol. 24, No. 18, pp. 3701-3706. https://doi.org/10.1080/0143116031000117047
  3. Harris, C. and Stephens, M. (1988). "A combined corner and edge detector." Proceedings, 4th Alvey Vision Conference, pp. 147-151.
  4. Ho, H. T. and Goecke, R. (2008). "Optical flow estimation using fourier mellin transform." IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8.
  5. Jing-zheng, L. and Xu-chu, Y. (2008). "Research on SAR image matching technology based on SIFT." The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Beijing, Vol. 37, pp. 403-407.
  6. Lowe, D. G. (2004). "Distinctive image features from scale-invariant Keypoints." International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  7. Maes, F., Vandermeulen, D. and Suetens, P. (2003). "Medical image registration using mutual information." Proceedings of the IEEE, Vol. 91, No. 10, pp. 1699-1722. https://doi.org/10.1109/JPROC.2003.817864
  8. Pluim, J. P. W., Maintz, J. B. A. and Viergever, M. A. (2000). "Image registration by maximization of combined mutual information and gradient information." Medical Image Computing and Computer-Assisted Intervention - MICCAI 2000, Vol. 1935/2000, pp. 452-461.
  9. Reddy, B. S. and Chatterji, B. N. (1996). "An FFT-Based technique for translation, rotation, and scale-invariant image registration." IEEE Transactions on image processing, Vol. 5, No. 8, pp. 1266-1271. https://doi.org/10.1109/83.506761
  10. Roche, A., Malandain, G. and Ayache, N. (1999). "Unifying maximum likelihood approaches in medical image registration." International Journal of Imaging Systems and Technology, Vol. 11, pp. 71-80.
  11. Safronov, K., Tchouchenkov, I. and Worn, H. (2006). "Combined medical image registration method using both mutual and gradient information." International Workshop on Computer Science and Information Technologies CSIT'2006, Vol. 1.
  12. Srinivasa R. B. and Chatterji, B. N. (1996). "An FFT-Based technique for translation, rotation, and scale-invariant image registration." IEEE Transactions on image processing, Vol. 5, No. 8, pp. 1266-1271. https://doi.org/10.1109/83.506761
  13. Suri, S. and Reinartz, P. (2010). "Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban areas." Geoscience and Remote Sensing, IEEE Transactions on, Vol. 48, No. 2, pp. 939-949. https://doi.org/10.1109/TGRS.2009.2034842
  14. Suri, S., Schwind, P., Uhl, J. and Reinartz, P. (2010). "Modifications in the SIFT operator for effective SAR image matching." International journal of Image and Data Fusion, Vol. 1, No. 3, pp. 243-256. https://doi.org/10.1080/19479832.2010.495322
  15. Wessel, B., Huber, M. and Roth, A. (2007). "Registration of near real-time SAR images by image-to-image matching." Proc. of Photogrammetric Image Analysis, pp. 179-184.
  16. Wolberg, G. and Zokai, S. (2000). "Robust image registration using log-polar transform." 2000 International Conference on Image Processing, Vol. 1, pp. 493-496.