Coupled neural networks for real-time road and obstacle recognition by intelligent road vehicles
Lampros Tsinas, Volker Graefe · 2005
Individual neural networks have been developed for specific recognition tasks within a system to be used by an intelligent road vehicle for recognizing traffic situations in real time. A set of networks, designed to cooperate in recognizing the own lane and obstacles on the lane is described. A video camera is used as a sensor. Separate neural networks are employed for different levels of processing and knowledge representation. The algorithms have been implemented on a PC. Results of real-time tests are reported.