DocumentCode :
288663
Title :
A neural network model of long-range apparent motion in the human vision
Author :
Kita, Hajime ; Sekine, Osamu ; Nihikawa, Y.
Author_Institution :
Dept. of Electr. Eng., Kyoto Univ., Japan
Volume :
4
fYear :
1994
fDate :
27 Jun-2 Jul 1994
Firstpage :
2254
Abstract :
Detection of motion is one of the most important functions of the visual systems of animals. Motion perceived by humans when succeeding frames are presented is called `apparent motion´. According to its psychophysical characteristics, a categorization of apparent motion into two parts has been proposed, i.e. the short-range apparent motion (SRAM) and the long-range one (LRAM). From a computational viewpoint, SRAM and LRAM are characterized by filtering and matching tasks, respectively. In this paper, a neural network model of LRAM is proposed. The model uses a neural network of the Hopfield type which solves the matching task as an optimization problem. Computer simulation shows that the network yields a satisfactory solution of the matching task with careful consideration of the energy function. Also, it is shown that the number of iterations required in the computation is in a plausible range for a model of human visual processing
Keywords :
Hopfield neural nets; biology computing; digital simulation; image matching; motion estimation; optimisation; visual perception; Hopfield neural network model; computer simulation; energy function; human visual processing; iterations; long-range apparent motion; matching task; optimization problem; psychophysical characteristics; successive frames; Animals; Filtering; Hopfield neural networks; Humans; Matched filters; Motion detection; Neural networks; Psychology; Random access memory; Visual system;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
Type :
conf
DOI :
10.1109/ICNN.1994.374568
Filename :
374568
Link To Document :
بازگشت