Abstract
We present two approaches for finding large man-made objects in outdoor scenes through the fusion of color and geometric information. We have tested our methods on images of concrete bridges. Both methods use a priori knowledge and models of bridges.
The first method has a 2-D model of a side view of the bridge. Rectangular features are extracted from the image. The corresponding surface material is estimated by a color matching algorithm. Next, an expert system uses Truth-Maintenance techniques to group features through the fusion of geometric relationships and color cues. It proposes hypotheses, and verifies them. Flexibility in the match allows for non-optimal conditions, such as oblique viewing angles (causing perspective distortion) or partial occlusions.
The other method consists of a 3-D hypothesized representation of the world, projected to 2-D for a tentative match with the image. The goals and issues are presented, and the proposed system architecture is described. Two completed subsystems for cue generation are shown: a vanishing point finder and a color-matcher.
This research was supported in part by ARO Contract DAAL03-87-K-0089.
Preview
Unable to display preview. Download preview PDF.
References
Baker, D.C., Aggarwal, J.K. and Hwang, S.S., “Geometry guided incremental segmentation”, IEEE Computer Vision Workshop, Miami Beach, FA., pp. 237–239, 1987.
Baker, D.C., Aggarwal, J.K. and Hwang, S.S., “Geometry guided segmentation of outdoor scenes”, Proc. S.IE, Orlando, FA., pp. 576–583, 1988.
Baker, D.C., Hwang, S.S. and Aggarwal, J.K., “Detection and segmentation of manmade objects in outdoor scenes: concrete bridges”, Journal of the Optical Society of America, A, pp. 938–950, June 1989.
Brooks, R.A., “Symbolic reasoning among 3-D models and 2-D images”, Artif. Intell., Vol. 17, pp. 285–348, 1981.
Burns, J.B., Hanson, A.R. and Riseman, E.M., “Extracting straight lines”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, No. 4, pp. 425–455, 1986.
Cheng, Y. and Kashyap, R. L., “A Study of Associative Evidential Reasoning”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 11, No. 6, pp. 623–631, June 1989.
Draper, B.A., Brolio, J., Collins, R.T., Hanson, A.R. and Riseman, E.M., “Image interpretation by distributed cooperative processes”, IEEE Conf. on Comp. Vision and Pattern Recog., Ann Arbor, MI., pp. 129–135, 1988.
Gershon, R., Jepson, A. D. and Tsotsos, J. K., “Highlight Identification Using Chromatic Information”, Proc. of the International Conf. on Computer Vision, London, pp. 161170, 1987.
Horaud, R., “New methods for matching 3-D objects with single perspective views”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 9, No. 3, pp. 401–412, 1987.
Hwang, S.S., Davis, L.S. and Matsuyama, T., “Hypothesis integration in image understanding systems”, Computer Vision, Graphics and Image Processing, Vol. 36, pp. 321–371, 1986.
Klinker, G.J., Shafer, S.A. and Kanade, T., “Using a color reflection model to separate highlights from object color”, Proc. of the International Conf. on Computer Vision, London, pp. 145–150, 1987.
Lehrer, N.B., Reynolds, G. and Griffith, J., “Initial hypothesis formation in image understanding using an automatically generated knowledge base”, Proc. of Darpa Image Understanding Workshop, Los Angeles, Vol. 2, pp. 521–537, 1987.
Magee, M.J. and Aggarwal, J.K., “Determining vanishing points from perspective images”, Computer Vision, Graphics and Image Processing, Vol. 26, No 2, pp. 256–267, 1984.
Mulder, J.A., Mackworth, A.K. and Havens, W.S., “Knowledge structuring and constraint satisfaction: the Mapsee approach”, IEEE Trans. Computers, Vol. 10, No 6, pp. 866–879, 1988.
Shortliffe, E.H., “Computer-based medical consultations: MYCIN”, Elsevier, New York, 1976.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lebègue, X.F., Baker, D.C., Aggarwal, J.K. (1993). Fusion of Color and Geometric Information. In: Aggarwal, J.K. (eds) Multisensor Fusion for Computer Vision. NATO ASI Series, vol 99. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-02957-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-662-02957-2_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08135-4
Online ISBN: 978-3-662-02957-2
eBook Packages: Springer Book Archive