The vision subsystem of an autonomous vehicle is studied. It is based on a multi layer perceptron that uses TV images to estimate the position of the vehicle. A comparative study of the effects of output data representation and input data pre processing is presented and discussed.
|Pages (from-to)||393 - 399|
|Number of pages||7|
|Journal||Neural Network World|
|Publication status||Published - 1996|
All Science Journal Classification (ASJC) codes