Title :
An adaptable time-delay neural-network algorithm for image sequence analysis
Author :
Wohler, Christian ; Anlauf, Joachim K.
Author_Institution :
DaimlerChrysler Res. & Technol., Ulm, Germany
fDate :
11/1/1999 12:00:00 AM
Abstract :
We present an algorithm based on a time-delay neural network with spatio-temporal receptive fields and adaptable time delays for image sequence analysis. Our main result is that tedious manual adaptation of the temporal size of the receptive fields can be avoided by employing a method to adapt the corresponding time delay and related network structure parameters during the training process
Keywords :
delays; image sequences; learning (artificial intelligence); neural nets; adaptable time-delay neural-network algorithm; image sequence analysis; spatio-temporal receptive fields; temporal size; training process; Backpropagation algorithms; Delay effects; Gray-scale; Image sequence analysis; Image sequences; Motion estimation; Neural networks; Neurons; Shape; Vehicle detection;
Journal_Title :
Neural Networks, IEEE Transactions on
