Biologically Based CAST-mechanism for Visual Motion Analysis

作者: Alexis Quesada-Arencibia , Roberto Moreno-Díaz , Miguel Aleman-Flores

DOI: 10.1007/3-540-45654-6_25

关键词: Receptive fieldObject (computer science)Machine visionMotion estimationComputer scienceRetinaWeightingComputer visionMotion analysisArtificial intelligence

摘要: In this paper we present a working vision system for estimating size, location and motion of an object by using set randomly distributed receptive fields on retina. The approach used here differs from more conventional ones in which the are arranged geometric pattern. From input level, computations performed parallel two different channels: one purely spatial properties, other time-space analysis, then at subsequent level to yield estimates size center gravity speed direction motion. Movement analysis refining is implemented lateral interaction (spatial) memory (temporal) schemes build trajectory. parameters involved (receptive field weighting function, number cells) tested speeds results compared, yielding new insights functioning living retina suggesting ideas improving artificial system.

参考文章(6)
Peter D. Scott, Applied Machine Vision Springer, New York, NY. pp. 439- 465 ,(1990) , 10.1007/978-1-4612-3406-7_15
Miguel Alemán-Flores, K. Nicholas Leibovic, Roberto Moreno-Díaz, A Computational Model for Visual Size, Location and Movement computer aided systems theory. pp. 406- 419 ,(1997) , 10.1007/BFB0025062
K.N. Leibovic, A model for information processing with reference to vision Journal of Theoretical Biology. ,vol. 11, pp. 112- 130 ,(1966) , 10.1016/0022-5193(66)90042-7
Ken Nakayama, Biological image motion processing: A review Vision Research. ,vol. 25, pp. 625- 660 ,(1985) , 10.1016/0042-6989(85)90171-3
E C Hildreth, C Koch, The Analysis of Visual Motion: From Computational Theory to Neuronal Mechanisms Annual Review of Neuroscience. ,vol. 10, pp. 477- 533 ,(1986) , 10.1146/ANNUREV.NE.10.030187.002401