Korean Journal of Remote Sensing (대한원격탐사학회지)

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

DOI QR Code

Building Roof Reconstruction in Remote Sensing Image using Line Segment Extraction and Grouping

선소의 추출과 그룹화를 이용한 원격탐사영상에서 건물 지붕의 복원

  • 예철수 (극동대학교 정보통신학부) ;
  • 전승헌 (서강대학교 전자공학과) ;
  • 이호영 (서강대학교 전자공학과) ;
  • 이쾌희 (서강대학교 전자공학과)
  • Published : 2003.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a method for automatic 3-d building reconstruction using high resolution aerial imagery. First, by using edge preserving filtering, noise is eliminated and then images are segmented by watershed algorithm, which preserves location of edge pixels. To extract line segments between control points from boundary of each region, we calculate curvature of each pixel on the boundary and then find the control points. Line segment linking is performed according to direction and length of line segments and the location of line segments is adjusted using gradient magnitudes of all pixels of the line segment. Coplanar grouping and pplygonal patch formation are performed per region by selecting 3-d line segments that are matched using epipolar geometry and flight information. The algorithm has been applied to high resolution aerial images and the results show accurate 3D building reconstruction.

본 논문에서는 고해상도의 항공 영상으로부터 건물의 3차원 정보를 자동으로 생성하는 방법을 제안하였다. 먼저 에지 보존 필터를 사용하여 영상에 포함된 잡음을 제거한 후에 watershed 기법을 이용하여 에지의 위치를 보존하고 영상 분할을 수행한다. 분할된 영역의 경계선에 위치한 화소의 곡률을 계산하여 control point를 검출하고 control point 사이의 선소를 추출한다. 추출된 선소들의 방향과 길이를 고려하여 선소의 연결을 수행하고 최종적으로 화소의 그레디언트 크기를 이용하여 선소의 위치를 조정한다. 공면의 그룹화와 다각형 조각을 형성하는 과정은 각 영역에 대해 공선 기하학과 비행 정보를 이용하여 정합된 3차원 선소들을 선택하여 이루어진다. 항공 영상에 제안한 방법을 적용하여 건물 지붕을 정확하게 검출할 수 있음을 보였다.

Keywords

References

  1. 대한원격탐사학회지 v.18 no.2 Hybrid 알고리듬을 이용한 원격탐사 영상의 분할 예철수;이쾌희 https://doi.org/10.7780/kjrs.2002.18.2.107
  2. Technical Report BIWI-TR-165 Segment stereo matching and coplanar grouping Bignone,F.
  3. Computer & Graphics v.19 no.1 Models for photogrammetric building reconstruction Braun,C.;T.H.Kolbe;F.Lang;W.Schickler;V.Steinhage;A.B.Cremers;W.Forstner;L.Plumer
  4. Proc. of International Symposium on Remote Sensing, EMSEA and KSRS Anisotropic diffusion for building segmentation form aerial imagery C.S.Ye;K.H.Lee
  5. Automatic Extraction of Man-Made Objects from Aerial and Space Images(Ⅱ) On the reconstruction of urban house roofs from aerial images Frere,D.;M.Hendrickx;J.Vandekerckhove;T.Moons;L.Van Gool
  6. IEEE Trans. Image Processing v.8 no.1 Image segmentation and analysis via multiscale gradient watershed hierarchies Gauch,J.M.
  7. Pattern Recognition v.23 Region matching and depth finding for 3-d objects in stereo aerial photographs H.J.Lee;W.L.Lei
  8. XIX Congress of ISPRS, Comm. IIII, Int. Archives of Photogrammetry and Remote Sensing v.31 Project AMOBE: Strategies, current status and future work Henricsson,O.;F.Bignone;W.Willuhn;F.Ade;O.Kubler;E.Baltsavias;S.Mason
  9. Computer Vision, Graphics, and Image Processing v.41 Detecting buildings in aerial images Huertas,A.;R.Nevatia
  10. IEEE Trans. Systems, Man and Cybernetics v.19 no.6 Methods for exploiting the relationship between buildings and their shadows on aerial imagery Irvin,R.B.;D.M.Mckeown
  11. ICASSP v.5 An Energy minimization approach to building detection in aerial images Krishnamachari,S.;R.Chellappa
  12. Internal Report High precision photogrammetric data set for building reconstruction and terrain modeling Mason S.;E.Baltsavias;D.Stallmann
  13. IEEE Trans. Pattern Anal. Machine Intell. v.11 no.11 Using perceptual organization to extract 3-d structures Mohan,R.;R.Nevatia
  14. IEEE Trans. Pattern Anal. Machine Intell. v.13 no.6 Watersheds in digital spaces: An efficient algorithm based on immersion simulations Vincent,L.;P.Soille
  15. XIX Congress of ISPRS, Comm. IIII, Int. Archives of Photogrammetry and Remote Sensing v.31 An approch to building extraction from digital surface models Weidner,U.