Abstract
The paper describes and compares stereo matching methods based on nonparametric image transformations. The new nonparametric measures for local neighborhoods of pixels are proposed as well. These are extensions to the well known Census transformation, successively used in many computer vision tasks. The resulting bit-fields are matched with the binary vectors comparison measures: Hamming, Tanimoto and Dixon-Koehler. The presented algorithms require only integer arithmetic what makes them very useful for real-time applications and hardware implementations. Many experiments with the presented techniques, employed to the stereovision, showed their robustness and competing execution times.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Banks, J., Bennamoun, M., Corke, P.: Non-Parametric Techniques for Fast and Robust Stereo Matching. CSIRO Manufacturing Science and Technology, Australia (1997)
Bhat, D.N., Nayar, S.K.: Ordinal Measures for Image Correspondence. IEEE Transaction on Pattern Analysis and Machine Intelligence 20(4) (1998)
Cyganek, B.: Neural Networks Application to The Correlation-Based Stereo-Images Matching. In: Proceedings of the 5th International Conference on Engineering Applications of Neural Networks EANN 1999, Warsaw, Poland, pp. 17–22 (1999)
Cyganek, B., Borgosz, J.: A Comparative Study of Performance and Implementation of Some Area-Based Stereo Algorithms. In: Skarbek, W. (ed.) CAIP 2001. LNCS, vol. 2124, pp. 709–716. Springer, Heidelberg (2001)
Cyganek, B.: Three Dimensional Image Processing, EXIT Warsaw (2002) (in Polish)
Cyganek, B., Borgosz, J.: An Object-Oriented Software Platform for Examination of Algorithms for Image Processing and Compression. In: Sloot, P.M.A., Abramson, D., Bogdanov, A.V., Gorbachev, Y.E., Dongarra, J., Zomaya, A.Y. (eds.) ICCS 2003. LNCS, vol. 2658, pp. 713–720. Springer, Heidelberg (2003)
Cyganek, B., Borgosz, J.: Fuzzy Nonparametric Measures for Image Matching. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 712–717. Springer, Heidelberg (2004)
Dixon, S.L., Koehler, R.T.: J. Med. Chem. 42, 2887–2900 (1999)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, Chichester (2001)
Fua, P.: A Parallel Stereo Algorithm that Produces Dense Depth Maps and Preserves Image Features, INRIA Technical Report No 1369 (1991)
Fusiello, A., et al.: Efficient stereo with multiple windowing. In: CVPR, pp. 858–863 (1997)
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision. In: CUP (2000)
Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C. The Art of Scientific Computing, 2nd edn. Cambridge University Press, Cambridge (1999)
Sloan Jr., K.R., Tanimoto, S.L.: Progressive Refinement of Raster Images. IEEE Transactions on Computers 28(11), 871–874 (1979)
Zabih, R., Woodfill, J.: Non-Parametric Local Transforms for Computing Visual Correspondence. In: Proc. Third European Conf. Computer Vision, pp. 150–158 (1994)
Zadeh, L.A.: Fuzzy sets. Information and Control 8, 338–353 (1965)
Zhengping, J.: On the Mutli-Scale Iconic Representation for Low-Level Computer Vision. Ph.D. Thesis. The Turing Institute and University of Strathclyde, pp. 114–118 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cyganek, B. (2004). Comparison of Nonparametric Transformations and Bit Vector Matching for Stereo Correlation. In: Klette, R., Žunić, J. (eds) Combinatorial Image Analysis. IWCIA 2004. Lecture Notes in Computer Science, vol 3322. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30503-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-540-30503-3_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23942-0
Online ISBN: 978-3-540-30503-3
eBook Packages: Computer ScienceComputer Science (R0)