Abstract
In this paper we propose a bio-inspired architecture for the visual reconstruction of silhouettes of moving objects, based on the behaviour of simple cells, complex cells and the Long-Range interactions of these neurons present in the primary visual cortex of the primates. This architecture was tested with real sequences of images acquired in natural environments. The results combined with our previous results show the flexibility of our propose since it allows not only to reconstruct the silhouettes of objects in general, but also, allows to distinguish between different types of objects in motion. This distinction is necessary since our future objective is the identification of people by their gait.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Cunado, D., Nixon, M., Carter, J.: Automatic extraction and description of human gait models for recognition purposes. Comput. Vis. Image Underst. 90, 1–41 (2003)
Moldenhauer, J., Boesnach, I., Stein, T.: Composition of complex motion models from elementary human motions. Articulated Motion and Deformable Objects 12, 68–77 (2006)
Xu, H., Jiwei, L., Lei, L., Zhiliang, W.: Gait recognition considering directions of walking. IEEE Cybernetics and Intelligent Systems, 1–5 (2006)
Mahmoudi, S., Daoudi, M.: A probabilistic approach for 3d shape retrieval by characteristic views. Pattern Recogn. Lett. 28(13), 1705–1718 (2007)
Yang, H.D., Lee, S.W.: Reconstruction of 3d human body pose from stereo image sequences based on top-down learning. Pattern Recogn. 40(11), 3120–3131 (2007)
Chen, H., Bhanu, B.: 3d free-form object recognition in range images using local surface patches. Pattern Recogn. Lett. 28(10), 1252–1262 (2007)
Yan, P., Bowyer, K.W.: A fast algorithm for icp-based 3d shape biometrics. Comput. Vis. Image Underst. 107(3), 195–202 (2007)
Lin, W.S., Fang, C.H.: Synthesized affine invariant function for 2d shape recognition. Pattern Recogn. 40(7), 1921–1928 (2007)
Mokhber, A., Achard, C., Milgram, M.: Recognition of human behavior by space-time silhouette characterization. Pattern Recogn. Lett. 29(1), 81–89 (2008)
Rogez, G., Orrite-Uruñuela, C., Martínez-del Rincón, J.: A spatio-temporal 2d-models framework for human pose recovery in monocular sequences. Pattern Recognition 41(9), 2926–2944 (2008)
Schlei, B.R.: A new computational framework for 2d shape-enclosing contours. CoRR cs.CV/0405029 (2004)
Shen, C., Lin, X., Shi, Y.: Human pose estimation from corrupted silhouettes using a sub-manifold voting strategy in latent variable space. Pattern Recogn. Lett. 30(4), 421–431 (2009)
Ahmad, M., Lee, S.W.: Human action recognition using shape and clg-motion flow from multi-view image sequences. Pattern Recogn. 41(7), 2237–2252 (2008)
Denman, S., Chandran, V., Sridharan, S.: An adaptive optical flow technique for person tracking systems. Pattern Recogn. Lett. 28(10), 1232–1239 (2007)
Laptev, I., Lindeberg, T.: Velocity-adapted spatio-temporal receptive fields for direct recognition of activities. IVC 22, 61–66 (2002)
Sereno, M.I., Dale, A.M., Belliveau, J.W., Brady, T.J., Rosen, B.R., Tootell, R.B.H.: Borders of multiple visual areas in humans revealed by functional magnetic resonance imaging. Science 268, 889–893 (1995)
Lerner, Y., Epshtein, B., Ullman, S., Malach, R.: Class information predicts activation by object fragments in human object areas. J. Cognitive Neuroscience 20(7), 1189–1206 (2008)
Van Essen, D.C., Anderson, C.H.: Information processing strategies and pathways in the primate retina and visual cortex, pp. 43–72. Academic Press Professional, Inc., San Diego (1990)
Kouh, M., Poggio, T.: A canonical neural circuit for cortical nonlinear operations. Neural Comput. 20(6), 1427–1451 (2008)
Giese, M., Poggio, T.: Neural mechanisms for the recognition of biological movements and acti on. Nature Reviews Neuroscience 4, 179–192 (2003)
Laxmi, V., Carter, J.N., Damper, R.I.: Biologically-inspired human motion detection. In: 10th European Symposium on Artificial Neural Networks, pp. 95–100 (2002)
Lange, J., Lappe, M.: The role of spatial and temporal information in biological motion perception. In: Advances in Cognitive Psychology, vol. 3, pp. 419–428. University of Muenster, Germany (2007)
Livingstone, M.S., Hubel, D.H.: Connections between layer 4b of area 17 and the thick cytochrome oxidase stripes of area 18 in the squirrel monkey. J. Neurosci. 7, 3371–3377 (1987)
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 (September 2000)
Collins, K.: 13. In the Primate Visual System, pp. 311–337. CRC Press, Boca Raton (2004)
Sirosh, J., Miikkulainen, R.: Topographic receptive fields and patterned lateral interaction in a self-organizing model of the primary visual cortex. Neural Computation 9(3), 577–594 (1997)
Bair, W., Cavanaugh, J.R., Movshon, J.A.: Time course and time-distance relationships for surround suppression in macaque v1 neurons. J. Neurosci. 23(20), 7690–7701 (2003)
Schwabe, L., Obermayer, K., Angelucci, A., Bressloff, P.C.: The role of feedback in shaping the extra-classical receptive field of cortical neurons: A recurrent network model. J. Neurosci. 26(36), 9117–9129 (2006)
Sánchez Orellana, P.L., Castellanos Sánchez, C.: A bio-inspired connectionist architecture for visual classification of moving objects. In: ICANN (1), pp. 982–990 (2008)
Hansen, T., Neumann, H.: A recurrent model of contour integration in primary visual cortex. J. Vis. 8(8), 1–25 (2008)
Castellanos Sánchez, C.: Neuromimetic indicators for visual perception of motion. In: 2nd International Symposium on Brain, Vision and Artificial Intelligence, vol. 103, pp. 134–143 (2007)
Kjaer, T.W., Gawne, T.J., Hertz, J.A., Richmond, B.J.: Insensitivity of V1 Complex Cell Responses to Small Shifts in the Retinal Image of Complex Patterns. J. Neurophysiol. 78(6), 3187–3197 (1997)
Lauritzen, T.Z., Miller, K.D.: Different Roles for Simple-Cell and Complex-Cell Inhibition in V1. J. Neurosci. 23(6), 10201–10213 (2003)
Ersoy, B., Kagan, I., Rucci, M., Snodderly, M.: Modeling the responses of v1 complex cells to natural temporal inputs. J. Vis. 4(8), 278–278 (2004)
Petkov, N., Kruizinga, P.: Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented visual stimuli: bar and grating cells. Biological Cybernetics 76(2), 83–96 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sánchez Orellana, P.L., Castellanos Sánchez, C. (2009). Bio-inspired Connectionist Architecture for Visual Detection and Refinement of Shapes. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds) Artificial Neural Networks – ICANN 2009. ICANN 2009. Lecture Notes in Computer Science, vol 5769. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04277-5_75
Download citation
DOI: https://doi.org/10.1007/978-3-642-04277-5_75
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04276-8
Online ISBN: 978-3-642-04277-5
eBook Packages: Computer ScienceComputer Science (R0)