Abstract
A recursive matching technique which uses the Kalman filtering for the recognition of 3D objects is presented. We make use of model based methodology in which both the models and scenes are assumed to be described by quadratic equations. The parameter matrices involved in the matrix form of quadratic equations are used in the matching process. The model features derived from these matrices are rotated and translated so as to match with those of the scene. The features consist of Euler parameters which represent the orientation of a surface and translation vector. The matching is formulated so as to apply the Kalman filter equations and the trace of the error covariance matrix (the error measure) guides the search process in pairing a model with a scene.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Besl, P.J. and Jain, R.C., Three-Dimensional Object Recognition, Computing Surveys, Vol. 17, No. 1, 1985, pp. 75–145.
Chin, R.T. and Dyer, C.R., Model-Based Recognition in Robot Vision, ACM Computing Surveys, Vol. 18, No. 1, 1986, pp. 67–108.
Chou, J.C.K. and Kamel, M., Quaternions approach to the Kinematic Equation of Rotation, AaAx = AxAb of a Robotic Manipulator, Proc. IEEE Int. Conf, on Robotics and Automation, Philadelphia, 1988, pp. 656–662.
Faugeras, O.D. and Hebert, M., A 3D Recognition and Positioning Algorithm using Geometrical Matching between Primitive Surfaces, Proc. 8th IJCAI, Karlschule, Germany, 1983, pp. 116–120.
Faugeras, O.D. and Hebert, M., The Representation, Recognition and Locating 3D Objects, Int. J. Robotics Research, Vol. 13, 1986, pp. 155–167.
Fisher, R.B., From Surfaces to Objects: Computer Vision and Three Dimensional Analysis, Wiley, New York, 1989.
Grimson, W.E.L. and Lozano-Perez, T., Model-Based Recognition and Localization from Sparse Range data or Tactile data, Int. J. Robotics Research, Vol. 3, 1984, pp. 3–35.
Hall, E.L., Tio, J.B.K., McPherson, C.A., Draper, C.S. and Sadjadi, F.A., Measuring Curved Surfaces for Robot Vision, Computer, Vol. 15, No. 12, 1982, pp. 42–54.
Hanmandlu, M., Rangaiah, C. and Biswas, K.K., Quadrics based matching technique for 3D Object Recognition, Image and Vision Computing, Vol. 10, No. 9, 1992, pp. 577–588.
Hanmandlu,M. and Shantaram, V., Contour Based Matching Technique for 3D Object Recognition using the Kalman filter, Proc. of 3rd Asian Conference on Computer Vision, Hong Kong, Jan. 8–11, 1998.
Paul, R.P., Robot Manipulators: Mathematics, Programming and Control, MIT Press, Cambridge, MA, 1981.
Press, W., Flannery, B., Teukolsky, S. and Vetterling, W., Numerical Recipes in C: The Art of Scientific Computing, Cambridge, 1986.
Sadjadi, F.A. and Hall, E.L., Three Dimensional Moment Invariants, IEEE Trans. on Pattern Analysis and Machine Intelligence., Vol. 2, 1980, pp. 127136.
Suk, M. and Bhandarkar, S.M., Three-Dimensional Object Recognition from Range Images, Springer-Verlag, Tokyo, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hanmandlu, M., Shantaram, V. (1997). Kalman filter based matching technique for 3D object recognition. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1351. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63930-6_155
Download citation
DOI: https://doi.org/10.1007/3-540-63930-6_155
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63930-5
Online ISBN: 978-3-540-69669-8
eBook Packages: Springer Book Archive