Korean Journal of Remote Sensing (대한원격탐사학회지)

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

DOI QR Code

Image registration using outlier removal and triangulation-based local transformation

이상치 제거와 삼각망 기반의 지역 변환을 이용한 영상 등록

  • Ye, Chul-Soo (Department of Ubiquitous IT, Far East University)
  • 예철수 (극동대학교 유비쿼터스IT학과)
  • Received : 2014.11.24
  • Accepted : 2014.12.20
  • Published : 2014.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents an image registration using Triangulation-based Local Transformation (TLT) applied to the remaining matched points after elimination of the matched points with gross error. The corners extracted using geometric mean-based corner detector are matched using Pearson's correlation coefficient and then accepted as initial matched points only when they satisfy the Left-Right Consistency (LRC) check. We finally accept the remaining matched points whose RANdom SAmple Consensus (RANSAC)-based global transformation (RGT) errors are smaller than a predefined outlier threshold. After Delaunay triangulated irregular networks (TINs) are created using the final matched points on reference and sensed images, respectively, affine transformation is applied to every corresponding triangle and then all the inner pixels of the triangles on the sensed image are transformed to the reference image coordinate. The proposed algorithm was tested using KOMPSAT-2 images and the results showed higher image registration accuracy than the RANSAC-based global transformation.

본 논문에서는 정합된 특징점 가운데 과대 오차를 포함한 정합점을 제거한 후에 삼각망 기반 지역 변환(Triangulation-based Local Transformation, TLT)을 이용한 영상 등록 방법을 제안한다. 기하 평균 기반의 코너 검출기를 통해 검출된 코너점에 대해 Pearson's correlation coefficient를 이용한 코너 정합을 수행하고 임계값 이상의 유사도를 가지는 코너 가운데 좌우 일관성 검사(Left-Right Consistency, LRC)를 통과한 코너를 1차 정합쌍으로 선정한다. 1차 정합쌍 가운데 RANSAC 기반 글로벌 변환(RANSAC-based Global Transformation, RGT) 오차가 이상치 임계값보다 작은 정합쌍을 최종 정합쌍으로 결정한다. 최종 정합쌍 코너를 이용해서 기준 영상과 관측 영상에서 Delaunay Triangulated Irregular Networks(TINs)을 각각 구성한 후에 서로 대응되는 각 삼각형마다 어파인 변환을 수행하고 각 삼각형 내부의 모든 화소들을 기준 영상 좌표로 변환한다. 제안한 알고리즘을 KOMPSAT-2 영상에 적용하여 RANSAC 기반 글로벌 변환보다 우수한 영상 등록 성능을 보임을 확인하였다.

Keywords

References

  1. Althof, R.J., M.G.J. Wind, and J.T. Dobbins, 1997. A rapid and automatic image registration algorithm with subpixel accuracy, IEEE Transactions on Medical Imaging, 16(3): 308-316. https://doi.org/10.1109/42.585765
  2. Castro, E.D. and C. Morandi, 1987. Registration of translated and rotated images using finite Fourier transform, IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(5): 700-703.
  3. Han, Y.K., D.J. Kim, and Y.I. Kim, 2011. Registration between high-resolution optical and SAR images using linear features, Korean Journal of Remote Sensing, 27(2): 141-150 (in Korean with English absract). https://doi.org/10.7780/kjrs.2011.27.2.141
  4. Kanade T. and M. Okutomi, 1994. A stereo matching algorithm with an adaptive window: theory and experiment, IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(9): 920-932. https://doi.org/10.1109/34.310690
  5. Lowe, D.G., 2004. Distinctive image features from scale-Invariant keypoints, International Journal of Computer Vision, 60(2): 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  6. Suri, S. and P. Reinartz, 2010. Mutual-information based registration of TerraSAR-X and ikonos imagery in urban areas, IEEE Transactions on Geoscience and Remote Sensing, 48(2): 939-949. https://doi.org/10.1109/TGRS.2009.2034842
  7. Viola, P. and W.M. Wells, 1997. Alignment by maximization of mutual information, International Journal of Computer Vision, 24(2): 137-154. https://doi.org/10.1023/A:1007958904918
  8. Ye, C.S., C.G. Moon, and J.H. Jeon, 2006. Stereo matching method using directional feature vector, Journal of Control, Automation, and Systems Engineering, 13(1): 152-57.
  9. Ye, C.S., 2011. Similarity measurement using Gabor energy feature and mutual information for image registration, Korean Journal of Remote Sensing, 27(6): 693-701. https://doi.org/10.7780/kjrs.2011.27.6.693
  10. Ye, C.S., 2014a. Mutual information-based circular template matching for image registration, Korean Journal of Remote Sensing, 30(5): 547-557 (in Korean with English absract). https://doi.org/10.7780/kjrs.2014.30.5.1
  11. Ye, C.S., 2014b. Corner detection based on geometric mean of eigenvalues, Proc. of 2014 KSRS Conference, Jeju, Korea, Oct. 16-17, pp.190-193.
  12. Ye, Y. and J. Shan, 2014. A local descriptor based registration method for multispectral remote sensing images with non-linear intensity differences, ISPRS Journal of Photogrammetry and Remote Sensing, 90: 83-95. https://doi.org/10.1016/j.isprsjprs.2014.01.009

Cited by

  1. Matching Points Extraction Between Optical and TIR Images by Using SURF and Local Phase Correlation vol.23, pp.1, 2015, https://doi.org/10.7319/kogsis.2015.23.1.081
  2. Extraction of water body in before and after images of flood using Mahalanobis distance-based spectral analysis vol.31, pp.4, 2015, https://doi.org/10.7780/kjrs.2015.31.4.2
  3. 다중 해상도 영상 등록을 위한 가변 원형 템플릿을 이용한 특징 정합 vol.34, pp.6, 2014, https://doi.org/10.7780/kjrs.2018.34.6.3.4