Abstract
We present an algorithm based on MRF modelling for motion detection in image sequences and give a modified version for implementation on analog resistive network. Energy minimization is realized by a network relaxing to its state of minimal power dissipation. It takes a few nanoseconds and replaces advantageously time consuming stochastic or suboptimal deterministic relaxation algorithms. The elementary cell of the network is presented along with the environment needed to feed it with the required inputs. Two network architectures are proposed, derived from CCD camera principle. Software simulations of a 128×128 network demonstrate the good behaviour of the modified algorithm on real sequences. Electrical simulations of a 16×16 network with ideal components give promising results. Implementation of the CMOS circuit with VLSI technology is under study at our laboratory.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Hutchinson J., Koch C., Luo J., Mead C., Computing motion using analog and binary resistive networks. Computer 21, 52–63 (1988)
Koch C., Marroquin J., Yuille A., Analog “neuronal” networks in early vision. Proc. Natl. Acad. Sci. USA, Biophysics 83, 4263–4267 (1986)
Luthon F., Caplier A., Motion detection and segmentation in image sequences using Markov Random Field modelling. Eurographics 93 Animation and Simulation Workshop, Barcelona, 265–275 (1993)
Geman S., Geman D., Stochastic relaxation, Gibbs distributions, and the bayesian restoration of images. IEEE Trans. PAMI 6, No 6, 721–741 (1984)
Lalande P., Bouthemy P., A statistical approach to the detection and tracking of moving objects in an image sequence. Signal Processing V: Theories and Applications, Elsevier Ed., Proc. of EUSIPCO, Barcelona, 947–950 (1990)
Besag J., On the statistical analysis of dirty pictures. J. Royal Statist. Soc. B 48, No 3, 259–302 (1986)
Hsu Y.Z., Nagel H.H., Rekers G., New likelihood test methods for change detection in image sequences. Comput. Vis. Graph. Im. Proces. 26, 73–106 (1984)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Luthon, F., Popescu, G.V., Caplier, A. (1994). An MRF based motion detection algorithm implemented on analog resistive network. In: Eklundh, JO. (eds) Computer Vision — ECCV '94. ECCV 1994. Lecture Notes in Computer Science, vol 800. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57956-7_19
Download citation
DOI: https://doi.org/10.1007/3-540-57956-7_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57956-4
Online ISBN: 978-3-540-48398-4
eBook Packages: Springer Book Archive