An Automatic Registration Algorithm for Two Overlapping Range Images
This paper describes a method of automatically performing the registration of two range images that have significant overlap. We first find points of interest in the intensity data that comes with each range image. Then we perform a tetrahedrization of the 3D range points associated with these 2D interest points. The triangle pairs of these tetrahedrizations are then matched in order to compute the registration. The fact that we have 3D data available makes it possible to effciently prune potential matches. The best match is the one that aligns the largest number of interest points between the two images. The algorithms are demonstrated experimentally on a number of different range image pairs.
KeywordsFeature Point Interest Point Range Image Iterative Close Point Interest Operator
Unable to display preview. Download preview PDF.
- 1.Ashbrook, A.P., R.B. Fisher, and C. Roberstson and N. Werghi (1998). Finding surface correspondences for object recognition using geometric histograms. In Computer Vision-ECCV98, Freiburg, Germany, pp. 674–686.Google Scholar
- 4.Cheng, C.-S., Y.-P. Hung, and J.-B. Chung (1998). A fast automatic method for registration of partially overlapping range images. In International Conference on Computer Vision, Bombay, India, pp. 242–248.Google Scholar
- 6.Clarkson, K., K. Mehlhorn, and R. Seidel (1993). Four results on randomized incremental constructions. In Computational geometry, theory and applications, pp. 85–121.Google Scholar
- 7.Gagnon, E., J.-F. Rivest, M. Greenspan, and N. Burtnyk (1996, June). A computer assisted range image registration system for nuclear waste cleanup. In IEEE Instrumentation and Measurement Conference, Brussels, Belgium, pp. 224–229.Google Scholar
- 8.Jasiobedzki97, P. (1997) Fusing and guding range measurements with colour video images. In International Conference on Recent Advances in 3D Digital-Imaging and Modelling, Ottawa, Canada, pp. 339–347.Google Scholar
- 9.Johnson, A. (1997) Surface matching by oriented points. In International Conference on Recent Advances in 3D Digital-Imaging and Modelling, Ottawa, Canada, pp. 121–129.Google Scholar
- 11.Rioux, M. (1994). Digital 3-d imaging: theory and applications. In Videometrics III, International Symposium on Photonic and Sensors and Controls for Commercial Applications, Volume 2350, pp. 2–15. SPIE.Google Scholar
- 12.Smith, S. and J. Brady (1997, May). Susan — a new approach to low level image processing. International Journal of Computer Vision, pp. 45–78.Google Scholar
- 14.Weik, S. (1997) Registration of 3d partial surfaces using luminance and depth information. In International Conference on Recent Advances in 3D Digital-Imaging and Modelling, Ottawa, Canada, pp. 93–100.Google Scholar
- 15.Wolfson, H. (1990). Model based object recognition by geometric hashing. In Computer Vision-ECCV90, pp. 526–536.Google Scholar
- 16.Zhang, Z. (1998, March). Determining the epipolar geometry and its uncertainty: a review. International Journal of Computer Vision 27(2).Google Scholar