Skip to main content
SpringerLink
Log in

A Novel Representation and Feature Matching Algorithm for Automatic Pairwise Registration of Range Images

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

Automatic registration of range images is a fundamental problem in 3D modeling of free-from objects. Various feature matching algorithms have been proposed for this purpose. However, these algorithms suffer from various limitations mainly related to their applicability, efficiency, robustness to resolution, and the discriminating capability of the used feature representation. We present a novel feature matching algorithm for automatic pairwise registration of range images which overcomes these limitations. Our algorithm uses a novel tensor representation which represents semi-local 3D surface patches of a range image by third order tensors. Multiple tensors are used to represent each range image. Tensors of two range images are matched to identify correspondences between them. Correspondences are verified and then used for pairwise registration of the range images. Experimental results show that our algorithm is accurate and efficient. Moreover, it is robust to the resolution of the range images, the number of tensors per view, the required amount of overlap, and noise. Comparisons with the spin image representation revealed that our representation has more discriminating capabilities and performs better at a low resolution of the range images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Ashbrook, A.P., Fisher, R.B., Robertson, C., and Werghi, N. 1998. Finding surface correspondence for object recognition and registration using pairwise geometric histograms. International Journal of Pattern Recognition and Artificial Intelligence, 2:674–686.

    Google Scholar 

  • Benjemma, R. and Schmitt, F. 1997. Fast global registration of 3D sampled surfaces using a multi-Z-buffer technique. In International Conference on Recent Advances in 3D Digital Imaging, pp. 113–120.

  • Besl, P. 1990. Machine Vision for Three-dimensional Scenes. Academic Press.

  • Besl, P.J. and McKay, N.D. 1992. Reconstruction of real-world objects via simultaneous registration and robust combination of multiple range images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):239–256.

    Article  Google Scholar 

  • Campbell, R.J. and Flynn, P.J. 2001. A survey of free-form object representation and recognition techniques. Computer Vision and Image Understanding, 81(2):166–210.

    Article  Google Scholar 

  • Chen, C., Hung, Y., and Cheng, J. 1991. RANSAC-based DARCES: A new approach to fast automatic registration of partially overlapping range images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(11):1229–1234.

    Google Scholar 

  • Chen, Y. and Medioni, G. 1991. Object modeling by registration of multiple range images. In IEEE International Conference on Robotics and Automation, pp. 2724–2729.

  • Cheng, J. and Don, H. 1991. A graph matching approach to 3-D point correspondences. International Journal of Pattern Recognition and Artificial Intelligence, 5(3):399–412.

    Article  Google Scholar 

  • Chua, C.S. and Jarvis, R. 1996. 3D free-form surface registration and object recognition. International Journal of Computer Vision, 17:77–99.

    Article  Google Scholar 

  • Chua, C.S. and Jarvis, R. 1997. Point signatures: A new representation for 3D object recognition. International Journal of Computer Vision, 25(1):63–85.

    Article  Google Scholar 

  • Curless, B. and Levoy, M. 1996. A volumetric method for building complex models from range images. In Computer Graphics, SIGGRAPH.

  • Foley, J., van Dam, A., Feiner, S.K., and Hughes, J.F. 1990. Computer Graphics-Principles and Practice, 2nd ed. Addison-Wesley.

  • Garland, M. 1999. Quadric-based polygonal surface simplification. Ph.D. thesis, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213.

    Google Scholar 

  • Garland, M. and Heckbert, P.S. 1997. Surface simplification using quadric error metrics. In SIGGRAPH, pp. 209–216.

  • Higuchi, K., Hebert, M., and Ikeuchi, K. 1994. Building 3-D models from unregistered range images. In IEEE International Conference on Robotics and Automation, vol. 3, pp. 2248–2253.

    Google Scholar 

  • Johnson, A.E. 1997. Spin images: A representation for 3-D surface matching. Ph.D. thesis, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213. Available along with range data at http://robotics.jpl.nasa.gov/people/johnson/thesis/thesis.html.

    Google Scholar 

  • Johnson, A.E. and Hebert, M. 1997. Surface registration by matching oriented points. In International Conference on Recent Advances in 3-D Imaging and Modelling, pp. 121–128.

  • Johnson, A.E. and Hebert, M. 1999. Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(5):674–686.

    Article  Google Scholar 

  • Lorensen, W.E. and Cline, H.E. 1987. A high resolution 3D surface construction algorithm. In Computer Graphics. ACM SIGGRAPH, pp. 163–169.

  • Mesh Tool Box, 2004. Vision and mobile robotics laboratory, Carnegie Mellon University, available at http://www-2.cs.cmu.edu/vmr/software/meshtoolbox/downloads.html.

  • Mian, A.S., Bennamoun, M., and Owens, R.A. 2004a. A novel algorithm for automatic 3D model-based free-form object recognition. In IEEE International Conference on Systems, Man and Cybernetics, pp. 6348–6353.

  • Mian, A.S., Bennamoun, M., and Owens, R.A. 2004b. From unordered range images to 3D models: A fully automatic multiview correspondence algorithm. In Theory and Practice of Computer Graphics. IEEE Computer Society Press, pp. 162–166.

  • Mian, A.S., Bennamoun, M., and Owens, R.A. 2004c. Matching tensors for automatic correspondence and registration. In European Conference on Computer Vision, vol. 2, pp. 495–505.

    Google Scholar 

  • Mian, A.S., Bennamoun, M., and Owens, R.A., 2004d. Performance analysis of an improved tensor based correspondence algorithm for automaic 3D modeling. In IEEE International Conference on Image Processing, pp. 1951–1954.

  • Nishino, K. and Ikeuchi, K. 2002. Robust simultaneous registration of multiple range images. In Asian Conference on Computer Vision, pp. 454–461.

  • Oishi, T., Sagawa, R., Nakazawa, A., Kurazume, R., and Ikeuchi, K. 2003. Parallel alignment of a large number of range images. In International Conference on 3-D Digital Imaging and Modeling, pp. 195–202.

  • Rangarajan, A., Chui, H., and Duncan, J. 1999. Rigid point feature registration using mutual information. Medical Image Analysis, 3(4):425–440.

    Article  Google Scholar 

  • Roth, G. 1999. Registering two overlapping range images. In IEEE International Conference on 3-D Digital Imaging and Modeling, pp. 191–200.

  • Rusinkiewicz, S. and Levoy, M. 2001. Efficient variants of the ICP algorithm. In 3DIM, pp. 145–152.

  • Stanford Computer Graphics Laboratory, 2001. A volumetric range image processing package. http://graphics.stanford.edu/software/vrip/.

  • Stanford Computer Graphics Laboratory, 2003. The Stanford 3D scanning repository. http://graphics.stanford.edu/data/3Dscanrep/.

  • Stephens, R.S. 1990. A probabilistic approach to the hough transform. In British Machine Vision Conference, pp. 55–59.

  • The University of Stuttgart, 2001. Stuttgart range image database. http://range.informatik.uni-stuttgart.de/htdocs/html/.

  • Williams, J. and Bennamoun, M. 2001. Simultaneous registration of multiple corresponding point sets. Computer Vision and Image Understanding, 81(1):117–142.

    Article  Google Scholar 

  • Wyngaerd, J.V., Gool, L.V., Koth, R., and Proesmans, M. 1999. Invariant-based registration of surface patches. In IEEE International Conference on Computer Vision, vol. 1, pp. 301–306.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Software Engineering, The University of Western Australia, 35 Stirling Highway, Crawley, WA, 6009, Australia

    A. S. Mian, M. Bennamoun & R. A. Owens

Authors
  1. A. S. Mian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Bennamoun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. R. A. Owens
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. S. Mian.

Additional information

This work has been provisionally patented under Australian patent number 2004902436 and is sponsored by ARC grant number DP0344338.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mian, A.S., Bennamoun, M. & Owens, R.A. A Novel Representation and Feature Matching Algorithm for Automatic Pairwise Registration of Range Images. Int J Comput Vision 66, 19–40 (2006). https://doi.org/10.1007/s11263-005-3221-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-005-3221-0

Keywords

Search

Navigation