Stereo Matching Strategy for 3-D Urban Modeling
This paper proposes an effective matching strategy to reconstruct 3-D urban models in densely built-up areas. Proposed scheme includes two main steps: feature-based image matching using building recognition technique and 3-D building reconstruction using the refined Rational Function Coefficients (RFCs). Especially, our approach is focused on improving the matching efficiency in complex urban scenes. For this purpose, we first performed automatic building recognition between stereo images, and then we endowed all points of building edges with identifiers using edge tracing method. Each identifier plays an important role in reducing search space for image matching within points of same building. A standard IKONOS stereo product was used to evaluate the proposed algorithms. It turned out that the proposed method could automatically determine the initial position and could dramatically reduce search space for point matching. Also, it was demonstrated that the updated RFCs could provide high-quality 3-D urban models.
KeywordsEdge Point Stereo Image Image Match Stereo Pair Epipolar Geometry
Unable to display preview. Download preview PDF.
- 1.Roux, M., Mckeown, D.M.: Feature matching for building extraction from multiple view. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 331–339 (1994)Google Scholar
- 2.Collins, R.T., Hanson, A.R., Riseman, M.R., Schultz, H.: Automatic extraction of buildings and terrain from aerial images. In: Automatic extraction of man-made objects from aerial images, pp. 169–178. Birkhauser Verlag, Basel (1995)Google Scholar
- 3.Bignone, F., Henricsson, O., Fua, P., Stricker, M.: Automatic extraction of generic house roofs from high-resolution aerial imagery. In: Computer Vision–ECCV 1996, vol. 1, pp. 85-96 (1996)Google Scholar
- 5.Sohn, H.G., Park, C.H., Heo, J.: 3-D building reconstruction using IKONOS multispectral stereo images. LNCS (LNAI), vol. 3863, pp. 62–68. Springer, Heidelberg (2005)Google Scholar
- 6.Kunii, Y., Chikatsu, H.: Efficient line matching by image sequential analysis for urban area modeling. In: ISPRS XXth Congress-Youth Forum, pp. 211–214 (2004)Google Scholar
- 7.Nakagawa, M., Shibasaki, R., Kagawa, Y.: Fusing stereo linear CCD image and laser range data for building 3D urban model. In: ISPRS Commission IV Workshop, WG IV/7 (2002)Google Scholar
- 9.Heipke, C.: Overview of image matching techniques. In: OEEPE-Workshop on the application of digital photogrammetric workstations, vol. 33, pp. 173–189Google Scholar
- 11.Grodecki, J., Dial, G.: IKONOS geometric accuracy. In: Joint Workshop of ISPRS Working group I/2, I/5 and IV/7 on High Resolution Mapping from space (2001)Google Scholar
- 12.Fraser, C.S., Hanley, H.B.: Bias compensation in rational functions for IKONOS satellite imagery. Photogrammetric Engineering & Remote Sensing 69(1), 53–57 (2003)Google Scholar