Abstract
The main aim of this work is to define a general algorithm to solve the well-known motion correspondence problem by minimizing an energy function where constraints leading to solution are defined. Starting from some approximated correspondences, estimated for features with high directional variance using radiometric similarity, optimal correspondence are obtained through an optimization technique. The new contribution of this work consists in the matching process based on refinement of raw measurements, in the energy function minimization technique converging to an optimal solution by taking advantage from some good initial guess, and in the applicability in a lot of contexts requiring motion correspondence just combining appropriate constraints functions. The approach has been tested in two common contexts: tracking of 3D coplanar points and passive navigation.
Preview
Unable to display preview. Download preview PDF.
References
L.Dreschler, H.Nagel ”Volumetric model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene” Comput. Graphics Image Processing Vol 20 pp 199–228(1982).
F.Glazer, G.Reynolds, P.Anandan ”Scene matching by hierarchical correlation” Proc. IEEE Conf. Comput. Vision Patt. Recogn. (1983).
E.C.Hildreth The measurement of visual motion Cambridge MA:MIT Press (1983).
W.Hoff, N. Ahuja ”Surfaces from stereo: Integrating feature matching, disparity estimation, and contour detection” IEEE Transactions PAMI Vol 11 No 2 (1989).
J.Weng, N.Ahuja, T.S.Huang ”Matching two perspective views” IEEE Transaction PAMI Vol 14 No 8 (1992).
P.Fua, ”Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities”. In Proc. IJCAI91.
J.Martin and J.L.Crowley ”Comparison of Correlation techniques” Intelligent Autonomous Systems U.Rembold et al. (Eds.), IOS Press, 1995.
J.P.Pascual Starink, E. Backer Finding point correspondences using simulated annealing, Pattern Recognition, Vol.28,No.2,1995.
H.P.Moravec The Stanford Cart and the CMU Rover,Proc. IEEE,1983.
S. Ullman The Interpretation of Visual Motion, MIT Press,1979.
J. Clark and A. Yuille, Data Fusion for sensory information processing systems, Kluwer Academic Publishers, 1990
J.J.Lee,J.Chang,Y.Ho Ha, Stereo Correspondence using the Hopfield Neural Network of a new energy function, Pattern Recognition, Vol.27,No.11, 1994.
N. M. Nasrabadi, C.Y. Choo, Hopfield Network for Stereo Vision Correspondence, IEEE Trans. Neural Networks, Vol. 3, No. 1, pp. 5–13, 1992.
N.M. Nasrabadi and Y.Liu, ”Stereo vision correspondence using a multichannel graph matching technique” Image and Vision Computing vol. 7, no.4, pp. 237–245, Nov. 1989
N.M.Nasrabadi ”A stereo vision technique using curve-segments and relaxiation matching” IEEE Trans PAMI vol. 13, Nov. 1991.
A.Rosenfeld, R.Hummel, and S.Zucker ”Scene labeling by relaxtion operations” IEEE Trans. Syst., Man, Cybern. vol. SMC-6, pp 420–453, June 1976.
S.Barnard and W.Thompson ”Disparity analysis of images” IEEE trans. PAMI vol. 2, pp 333–340, July 1980.
J.Hopfield and D.W.Tank, ” Neural computation of decisions in the optimization problems” Biol Cybern. vol. 52, pp 141–152, 1985.
S.Krikpatrick, C.D.Gellatt, Jr., and M.P.Vecchi, ”Optimization by simulated anealling” Science vol. 220, no.4598, pp. 671–680, May 1983.
O.Axelsson and V.A.Barker Finite Element Solution of Boundary Value Problems: Theory and Computation, Academic Press, 1984.
A.Blake and A.Zisserman Visual Reconstruction, MIT Press, 1987.
Y.T.Zhou, R. Chellappa, A Neural Network for Motion Processing, In Neural Network Perception, Vol. 1, Academic Press, 1992.
M.S.Mousavi, R. J. Schalkoff, ANN Implementation od Stereo Vision Using a Multi-layer Feedback Architecture, IEEE trans. on Neural Network, Vol.24,No.8,1994.
J.M.Cruz,G.Pajares,J.Aranda, A neural network Model in stereovision Matching, Neural Networks,Vol.8,No.5,1995.
B.W.Lee and B.J.Sheu ”Combinatorial Optimization Using Competitive-Hopfield Neural Network”
D.R.Uecker and H.Sakou ”Point pattern matching using a Hopfield-type Neural Network”
P.Gurdjos, P.Dalle, S.Castane ”Tracking 3D Coplanar Points in the Invariant Perspective Coordinates Plane” Proc. of ICPR '96 Vienna 1996.
O.Faugeras Three Dimensional Computer Vision MIT Press, Cambridge, MA, 1992.
A.Branca, E.Stella, A.Distante ”Feature Matching by Optimization using Environmental Constraints ” Proc. of Time Varying Image Processing and Object Recognition Firenze 1996.
A.Branca, E.Stella, G.Attolico, A.Distante ”Stereo Matching by optimization using weak environmental constraints” Proc. of SPIE96 Boston 1996.
A.Branca, E.Stella, A.Distante ”Passive Navigation using Focus of Expansion” Proc. of Workshop on applications of computer vision Sarasota 1996.
A.Branca, G.Cicirelli, E.Stella, A.Distante ”Mobile Vehicle's Egomotion Estimation from Time Varying Image Sequences ” Proc. of ICRA97 New Mexico 1996 (submitted).
R.C.Nelson, J.Aloimonos, Obstacle Avoidance Using Flow Field Divergence, IEEE Trans. on Patt. Anal. and Mach. Intell., VOL.11, NO. 10. Oct. '89.
C.Fermuller Passive Navigation Int. Journal of Computer Vision, 14(2):147–158, March 1995.
C.Fermuller Qualitative egomotion Int. Journal of Computer Vision, 15(1/2):7–29, 1995.
W.Burger, B.Bhanu, Estimating 3D Egomotion from Perspective Image Sequences, IEEE Trans. on PAMI, Vol. 12, No. 18,pp. 1040–1058, Nov. 1990.
E.De Micheli, V.Torre, S.Uras, The accuracy of the computation of optical flow and of the recovery of motion parameters, III Trans. on Patt. Anal. and Mach. Intell.,vol. 15, n.5, May '93.
R.Hummel, V.Sundareswaran Motion Parameter Estimation from Global Flow Field Data, IEEE Trans. on Patt. Anal. and Mach. Intell., vol.15, no.5, May '93.
F.G.Meyer, Time to collision from first-order models of the motion field, IEEE Trans. on Rob. and Autom., VOL.10, NO. 6, Dec. '94
K.Prazdny, Determining the Instantaneous Direction of Mo tion from Optical Flow Generated by a Curvilinearly Moving Observer, CGIP, Vol. 17, pp. 238–248, 1981.
Y.Ohta and T.Kanade, ”Stereo by Intr-and Inter-Scanline Search. IEEE Trans. on Pat. Anal, and Mach. Intell., 7, No.2:139–154, 1985.
A.Meygret, M.Thonnat, and M.Berthold, ”A pyramidal Stereovision Algorithm Based on Contour Chain points”. In Proc. European Conf. on Comp. Vision Antibes, France, April 1990. Springer-Verlag.
L.Robert and O.D.Faugeras ”Curve-based Stereo: Figural Continuity and Curvature” In CVPR91, 57–62.
N.Ayache and B.Faverjon, ”Efficient Registration of Stereo Images by Matching Graph. Descriptions of Edges Segments” The Int. Journal of Comp. Vision 1(2):107–131, April 1987.
D.Marr, T.Poggio, ”A computational theory of human stereo vision”, Proc. of Royal Society of London B, Vol.204.
N.Ayache, ”Artificial Vision for Mobile Robots”,MIT Press, 1991
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Branca, A., Stella, E., Distante, A. (1997). Motion correspondence through energy minimization. In: Pelillo, M., Hancock, E.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 1997. Lecture Notes in Computer Science, vol 1223. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62909-2_102
Download citation
DOI: https://doi.org/10.1007/3-540-62909-2_102
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62909-2
Online ISBN: 978-3-540-69042-9
eBook Packages: Springer Book Archive