Abstract
We describe a general approach to integrate the information produced by different visual modules with the goal of generating a quantitative 3D reconstruction of the observed scene and to estimate the reconstruction errors.
The integration is achieved in two steps. Firstly, several different visual modules analyze the scene in terms of a common data representation: planar patches are used by different visual modules to communicate and represent the 3D structure of the scene. We show how it is possible to use this simple data structure to share and integrate information from different visual modalities, and how it can support the necessities of the great majority of different visual modules known in literature. Secondly, we devise a communication scheme able to merge and improve the description of the scene in terms of planar patches. The applications of state-of-the-art algorithms allows to fuse information affected by an unknown grade of correlation and still guarantee conservative error estimates.
Tests on real and synthetic scene show that our system produces a consistent and marked improvement over the results of single visual modules, with error reduction up to a factor of ten and with typical reduction of a factor 2–4.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Aloimonos, J. and Shulman, D. 1989. Integration of Visual Modules—An Extension of the Marr Paradigm. Academic Press: London.
Calibrated Imaging Laboratory home page. http://www.cs.cmu.edu/∼cil/cil-ster.html
Cozzi, A., Crespi, B., Valentinotti, F., and Wörgötter, F. 1997. Performance of pahse-based algorithms for disparity estimation. Machine Vision abd Applications, 9(5-6):334-340.
Eckhorn, R., Bauer, R., Jordan, W., Kruse, B.M.W., Munk, M., and Reitböck, H. 1988. Coherent oscillations: A mechanism of feature linking in the visual cortex? Biological Cybernetics, 60:121-130.
Faugeras, O. 1993. Three-Dimensional Computer Vision. MIT Press: Cambridge.
Fleet, D., Jepson, A., and Jenkin, M. 1991. Phase-based disparity measurement. Computer Vision, Graphic and Image Processing, 53(2):198-210.
Fua, P., Leclerc, Y., and Loung 1999. Characterizing the performance of multiple-image point-correspondence algorithms using self-consistency. In Proceedings of: The Vision Algorithms: Theory and Practice Workshop (ICCV99), Corfu, Greece.
Fua, P. and Leclerc, Y.G. 1995. Object-centered surface reconstruction: Combining multi-image stereo and shading. IJCV, 16:35-56.
Gamble, E. and Poggio, T. 1987. Visual integration and detection of discontinuities: The key role of intensity edges. A.I. Memo 970, MIT, Artificial Intelligent Laboratory.
Geman, S. and Geman, D. 1984. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Intelligence, 6(6):721-741.
Haralick, R.M. 1996. Propagating covariance in computer vision. In Workshop on Performance Characteristics of Vision Algorithms, H.I. Christensen, W. Förstner, and C.B. Madsen (Eds.), Cambridge, UK, pp. 1-12.http://www.vision.auc.dk/∼hic/performance-ws.html
Irani, M. and Anandan, P. 1996. Parallax geometry of pairs of points for 3d scene analysis. In Proc. 4th European Conf. on Computer Vision, Cambridge, Cambridge, UK, Vol. 1, pp. 17-30.
Kanatani, K. 1990. Group-Theoretical Methods in Image Understanding, volume 20 of Springer Series in information Sciences. Springer-Verlag: Berlin, Heidelberg.
Lucas, B. and Kanade, T. 1984. Optical navigation by the method of differences. In DARPA84, pp. 272-281.
Maybeck, P.S. 1979. Stochastic Models, Estimation, and Control, vol. 1 of Mathematics in Science and Engineering. Academic Press: New York.
Opara, R. and Wörgötter, F. 1998. A fast and robust cluster update algorithm for image segmentation in spin-lattice models without annealing-visual latencies revisited. Neural Computation, 10:1547-1566.
Pankanti, S. and Jain, A.K. 1995. A uniform bayesian framework for integration. Technical Report, Michigan State University.
Poggio, T.A., Gamble, E., and Little. J.J. 1988. Parallel integration of vision modules. Science, 242:436-439.
Press, W.H., Teukolsky, S.A., Vetterling, W.T., and Flannery, B.P. 1992. Numerical Recipes in C. Cambridge University Press, second edn.
Singer, W. and Gray, C.M. 1995. Visual feature integration and the temporal correlation hypothesis. Annu. Rev. Neurosci., 18:555-586.
Uhlmann, J.K. 1997. A culminating advance in the theory and practice of data fusion, filtering, and decentralized estimation. Technical report. Covariance Intersection Working Group.http://www.ait.nrl.navy.mil/people/uhlmann/covlnt.html.
Wang, D. and Terman, D. 1997. Image segmentation based on oscilatory correlation. Neural Computation, 9:1623-1626.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cozzi, A., Wörgötter, F. COMVIS: A Communication Framework for Computer Vision. International Journal of Computer Vision 41, 183–194 (2001). https://doi.org/10.1023/A:1011156004656
Issue Date:
DOI: https://doi.org/10.1023/A:1011156004656