Abstract
This paper presents a bio-inspired connectionist approach for motion description through sequences of images. First, this approach is based on the architecture of oriented columns and the strong local and distributed interactions of the neurons in the primary visual cortex (V1). Secondly, in the integration and combination of their responses in the middle temporal area (MT). I propose an architecture in two layers : a causal spatio-temporal filtering (CSTF) of Gabor-like type which captures the oriented contrast and a mechanism of antagonist inhibitions (MAI) which estimates the motion. The first layer estimates the local orientation and speed, the second layer classifies the motion (global response) and both describe the motion and the pursuit trajectory. This architecture has been evaluated on sequences of natural and synthetic images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
McCane, B., Novins, K., Grannitch, D., Galvin, B.: On benchmarking optical flow. Computer Vision and Image Undestanding, 126–143 (2001)
Castellanos-Sánchez, C.: Neuromimetic connectionist model for embedded visual perception of motion. PhD thesis, Université Henri Poincaré (Nancy I), Nancy, France, Bibliothèque des Sciences et Techniques (2005)
Fellez, W.A., Taylor, J.G.: Establishing retinotopy by lateral-inhibition type homogeneous neural fields. Neurocomputing 48, 313–322 (2002)
Latham, P.E., Nirenberg, S.: Computing and stability in cortical networks. Neural Computation, 1385–1412 (2004)
Moga, S.: Apprendre par imitation: une nouvelle voie d’apprentissage pour les robots autonomes. PhD thesis, Université de Cergy-Pontoise, Cergy-Pontoise, France (2000)
Simoncelli, E.P., Heeger, D.J.: A model of neural responses in visual area mt. Visual Research 38(5), 743–761 (1998)
Mingolla, E.: Neural models of motion integration and segmentation. Neural Networks 16, 939–945 (2003)
Pack, C., Grossberg, S., Mingolla, E.: A neural model of smooth pursuit control and motion perception by cortical area mst. Technical Report CAS/CNR-TR-99-023, Department of Cognitive and Neural Systems and Center for Adaptive Systems, Boston University, 677 Beacon St, Boston, MA 02215 (2000)
Zemel, R.S., Sejnowski, T.J.: A model for encoding multiple object motions and self-motion in area mst of primate visual cortex. The Journal of Neurosciences 18(1), 531–547 (1998)
Castellanos-Sánchez, C., Girau, B., Alexandre, F.: A connectionist approach for visual perception of motion. In: Smith, L., Hussain, A., Aleksander, I. (eds.) Brain Inspired Cognitive Systems (BICS 2004), vol. BIS3–1, pp. 1–7 (2004)
Pollen, D., Ronner, S.: Phase relationships between adjacent simple cells in the visual cortex. Science 212, 1409–1411 (1981)
Newsome, W.T., Gizzi, M.S., Movshon, J.A.: Spatial and temporal properties of neurons in macaque mt. Investigative Ophtalmology and Visual Science Supplement 24, 106 (1983)
Hammond, P., Reck, J.: Influence of velocity on directional tuning of complex cells in cat striate cortex for texture motion. Neuroscience Letters 19, 309–314 (1981)
Torres-Huitzil, C., Girau, B., Castellanos-Sánchez, C.: On-chip visual perception of motion: A bio-inspired connectionist model on fpga. Neural Networks 18(5-6), 557–565 (2005)
Torres-Huitzil, C., Girau, B.: Fpga implementation of an excitatory and inhibitory connectionist model for motion perception. In: Brebner, G.J., Chakraborty, S., Wong, W.F. (eds.) IEEE International Conference on Field-Programmable Technology, FPT 2005, pp. 259–266 (2005)
Castellanos-Sánchez, C., Girau, B.: Dynamic pursuit with a bio-inspired neural model. In: Blanc-Talon, J., Philips, W., Popescu, D.C., Scheunders, P. (eds.) ACIVS 2005. LNCS, vol. 3708, pp. 284–291. Springer, Heidelberg (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Castellanos-Sánchez, C. (2007). A Bio-inspired Connectionist Approach for Motion Description Through Sequences of Images. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74695-9_59
Download citation
DOI: https://doi.org/10.1007/978-3-540-74695-9_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74693-5
Online ISBN: 978-3-540-74695-9
eBook Packages: Computer ScienceComputer Science (R0)