Abstract
Bio-inspired energy models compute motion along the lines suggested by the neurophysiological studies of V1 and MT areas in both monkeys and humans: neural populations extract the structure of motion from local competition among MT-like cells. We describe here a neural structure that works as a dynamic filter above this MT layer for image segmentation and takes advantage of neural population coding in the cortical processing areas. We apply the model to the real-life case of an automatic watch-out system for car-overtaking situations seen from the rear-view mirror. The ego-motion of the host car induces a global motion pattern whereas an overtaking vehicle produces a pattern that contrasts highly with this global ego-motion field. We describe how a simple, competitive, neural processing scheme can take full advantage of this motion structure for segmenting overtaking-cars
Similar content being viewed by others
References
K. Nakayama (1985) ArticleTitleBiological image motion processing: a review Vision Research 25 IssueID5 625–660 Occurrence Handle10.1016/0042-6989(85)90171-3 Occurrence Handle3895725
Adelson, E. H. and Bergen, J. R.: The extraction of spatiotemporal energy in human and machine vision. In: Proceeding of IEEE Workshop on Motion: Representation and Analysis, Charleston, SC, pp. 151–156, 1986
D.J. Heeger (1987) ArticleTitleModel for the extraction of image flow Journal of the Optical Society of America 4 IssueID8 1455–1471 Occurrence Handle3625326
E.P. Simoncelli D.J. Heeger (1998) ArticleTitleA model of neuronal responses in visual area MT Vision Research 38 IssueID5 743–761 Occurrence Handle10.1016/S0042-6989(97)00183-1 Occurrence Handle9604103
D.H. Hubel T.N. Wiesel (1962) ArticleTitleReceptive fields, binocular interactions and functional architecture in the cat’s visual cortex Journal of Physiology 160 106–154 Occurrence Handle14449617
Simoncelli E.P. Distributed analysis and representation of visual motion, PhD thesis,Massachusetts Institute of Technology, Deptartment of Electrical Engineering Computer Science, Cambridge, MA., 1993
Bors A.G., Pitas I. (1997). Moving scene segmentation using median radial basis function network. In Proceedings of IEEE Symposium on Circuits and Signals (ISCAS’97) Vol. I, pp. 529–532, Hong Kong
Chen Y.-K., Kung S.Y. (1996). A multi-module minimization neural network for motion-based scene segmentation. In Proceedings of IEEE Workshop on Neural Networks for Signal Processing, pp.371–380, Kyoto, Japan
B.E. Shi K.A. Boahen (2002) ArticleTitleCompetitively coupled orientation selective cellular neural networks IEEE Transactions on Circuits and Systems I 49 IssueID3 388–394 Occurrence Handle10.1109/81.989177
E. Ros J. Pelayo F. D. Palomar I. Rojas J.L. Bernier A. Prieto (1999) ArticleTitleStimulus correlation and adaptive local motion detection using spiking neurons International Journal of Neural Systems 9 IssueID5 485–490 Occurrence Handle10.1142/S0129065799000526 Occurrence Handle10630482
R.R. Harrison C. Koch (2000) ArticleTitleA robust analog VLSI Reichardt motion sensor Analog Integrated Circuits and Signal Processing 24 213–229 Occurrence Handle10.1023/A:1008361525235
Andreou A.G., Strohbehn K. (1990). Analog implementation of the Hassenstein-Reichardt-Poggio models for vision computation. In Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, pp. 707–710
A.A. Stocker (2004) ArticleTitleAnalog VLSI focal-plane array with dynamic connections for the estimation of piecewise-smooth optical flow IEEE Transactions on Circuits and Systems-Special Issue on CNN Technology and Active Wave Computing 51 IssueID5 963–973
J. Kramer R. Sarpeshkar C. Koch (1997) ArticleTitlePulse-based analog VLSI velocity sensors IEEE Transaction Circuits and System II: Analog and Digital Signal Processing 44 IssueID2 86–101 Occurrence Handle10.1109/82.554431
G. Indiveri (2004) Smart adaptive systems on silicon M Valle (Eds) Neuromorphic Engineering Kluwer Academic Publishers Boston, MA
R. Etienne-Cummings (1999) ArticleTitleIntelligent robot vision sensors in VLSI Autonomous Robots 7 225–237 Occurrence Handle10.1023/A:1008968319725
Stocker, A. and Simoncelli, E.: Constraining a bayesian model of human visual speed perception. In Proceedings of NIPS Neural Information Processing Systems 17, Vancouver, Canada, 2004.
J. Barron D. Fleet S. Beauchemin (1994) ArticleTitlePerformance of optical flow techniques International Journal of Computer Vision 12 IssueID1 43–77 Occurrence Handle10.1007/BF01420984
H. Liu T. H. Hong M. Herman T. Camus R. Chellappa (1998) ArticleTitleAccuracy vs. efficiency trade-offs in optical flow algorithms Computer Vision and Image Understanding 72 IssueID3 271–286 Occurrence Handle10.1006/cviu.1998.0675
B. McCane K. Novins D. Crannitch B. Galvin (2001) ArticleTitleOn benchmarking optical flow Computer Vision and Image Understanding 84 126–143 Occurrence Handle10.1006/cviu.2001.0930
U. Franke D. Gavrila A. Gern S. Görzig R. Janssen F. Paetzold C. Wöhler (2000) From door to door- principles and application on computer vision for driver assistant systems L Vlasic F. Harashima M. Parent (Eds) Intelligent Vehicle Technologies: Theory and Applications Butterworth London, UK 131–188
Handmann, U., Kalinke, T., Tzomakas, C., Werner, M. and von Seelen, W.: Computer vision for driver assistance systems. In Proceedings of SPIE. Vol. 3364 pp. 136–147, Orlando, 1998.
Görzig S. and Franke U., ANTS-Intelligent vision in urban traffic, in IEEE Conference on Intelligent Transportation Systems, Stuttgart 1998.
H. B. Barlow (1978) ArticleTitleThe efficiency of detecting changes of intensity in random dot patterns Vision Research 18 IssueID6 637–650 Occurrence Handle10.1016/0042-6989(78)90143-8 Occurrence Handle664351
D.J. Field A. Hayes R.F. Hess (1993) ArticleTitleContour integration by the human visual system: evidence for local “association field” Vision Research 33 IssueID2 173–193 Occurrence Handle10.1016/0042-6989(93)90156-Q Occurrence Handle8447091
J. Saarinen M Levi D. B. Shen (1997) ArticleTitleIntegration of local pattern elements into a global shape in human vision In Proceeding of the National Academic of Sciences USA 94 8267–8271 Occurrence Handle10.1073/pnas.94.15.8267
C. D. Gilbert T. N. Wiesel (1985) ArticleTitleIntrinsic connectivity and receptive field properties in visual cortex Vision Research 25 IssueID3 365–374 Occurrence Handle10.1016/0042-6989(85)90061-6 Occurrence Handle3895724
D. H. Grosof R. M. Shapley M. J. Hawken (1993) ArticleTitleMacaque V1 neurons can signal ‘illusory’ contours Nature 365 550–552 Occurrence Handle8413610
D. H. Hubel (1988) Eye, Brain and Vision Scientific American Library New York
Lettvin, J. Y., Maturana, H. R., McCulloch, W. S. and Pitts, W. H.: What the frog’s eye tells the frog’s brain, in Proceedings of IRE, 47, pp. 1940–1951, 1959.
C. Enroth-Cugell J. C. Robson (1966) ArticleTitleThe contrast sensitivity of retinal ganglion cells of the cat Journal of Physiology 187 517–552
Mota, S., Ros, E., Díaz, J., Botella, G.,Vargas, F. and Prieto, A.: Motion driven segmentation scheme for car overtaking sequences. In Proceedings of 10th International Conference on Vision in Vehicles (VIV’2003), Granada, Spain, 2003.
J. Díaz E. Ros S. Mota R. Carrillo R. Agís (2004) ArticleTitleReal time optical flow processing system Lecture Notes in Computer Science 3203 617–626
S. Mota E. Ros J. Díaz E. M. Ortigosa R. Agís R. Carrillo (2004) ArticleTitleReal-time visual motion detection of overtaking cars for driving assistance using FPGAs Lecture Notes in Computer Science 3203 1158–1161
van Vliet, L. J., Young, I. T. and Verbeek, P. W.: Recursive gaussian derivative filters. In Proceedings of the 14th International Conference on Pattern Recognition, ICPR’98, 509–514, Brisbane, Australia, 1998.
A. Fernández-Caballero J. Mira M. A. Fernández A. E. Delgado (2003) ArticleTitleOn motion detection through a multi-layer neural network architecture Neural Network 16 205–222 Occurrence Handle10.1016/S0893-6080(02)00233-2
D. J. Heeger (1992) ArticleTitleNormalization of cell responses in cat striate cortex Visual Neuroscience 9 IssueID2 181–198 Occurrence Handle1504027
D. J. Fleet H. Wagner D. J. Heeger (1996) ArticleTitleNeural encoding of binocular disparity: energy models, position shifts and phase shifts Vision Research 36 IssueID12 1839–1857 Occurrence Handle10.1016/0042-6989(95)00313-4 Occurrence Handle8759452
W. T. Freeman E. H. Adelson (1991) ArticleTitleThe design and use of steerable filters IEEE Pattern Analysis and Machine Intelligence 13 IssueID9 891–906 Occurrence Handle10.1109/34.93808
Watson, A. B. and Ahumada, A. J.: A look at motion in the frequency domain, In: Tsosos, J.K. (ed.), Motion: Perception and representation, pp. 1–10. New York, 1983.
W. J. H. Nauta M. Freitag (1986) Fundamental Neuroanatomy W.H. Freeman New York
N. M. Grzywacz A. L. Yuille (1990) ArticleTitleA model for the estimate of local velocity by cells in the visual cortex Proceedings of the Royal Society of London B 239 129–161
Sperling, G., Chubb, C., Solomon, J. A. and Lu, Z. -L.: Full-wave and half-wave processes in second order motion and texture, inWiley (Ciba Foundation Symposium, 184) Higher-order processing in the visual system, pp. 287–303, Chichester: U.K, 1994.
Young, R. A.: Simulation of human retinal function with the Gaussian derivative model, in Proceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,pp. 564–569, Miami, FL, 1986.
Frye, R. E. and Ledley, R. S.: Derivative of Gaussian functions as receptive field models for disparity sensitive neurons of the visual cortex, Proceedings of the 1996 Fifteenth Southern Biomedical Engineering Conference, pp. 270–273, 1996.
E. P. Simoncelli H. Farid (1996) ArticleTitleSteerable wedge filters for local orientation analysis IEEE Trans Image Proceedings 5 IssueID9 1377–1382 Occurrence Handle10.1109/83.535851
J. J. Koenderink A. J. Doom Particlevan (1987) ArticleTitleRepresentation of local geometry in the visual system Biological Cybernetics 55 IssueID6 367–375 Occurrence Handle10.1007/BF00318371 Occurrence Handle3567240
J. A. Bloom T. R. Reed (1996) ArticleTitleA Gaussian derivative-based transform IEEE Transactions on Image Processing 5 IssueID3 551–553 Occurrence Handle10.1109/83.491330
Young, R. A. and Lesperance, R. M., A physiological model of motion analysis for machine vision, in Proc. of the SPIE, 1913 pp. 48–123, San Jose, CA, 1993.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mota, S., Ros, E., Díaz, J. et al. Motion-Driven Segmentation by Competitive Neural Processing. Neural Process Lett 22, 125–147 (2005). https://doi.org/10.1007/s11063-005-2158-1
Issue Date:
DOI: https://doi.org/10.1007/s11063-005-2158-1