Title :
Coupled neural networks for real-time road and obstacle recognition by intelligent road vehicles
Author :
Tsinas, Lampros ; Graefe, Volker
Author_Institution :
Inst. fur Messtech., Univ. der Bundeswehr Munchen, Neubiberg, Germany
Abstract :
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.
Keywords :
image recognition; intelligent control; knowledge representation; mobile robots; neural nets; real-time systems; road vehicles; PC; coupled neural networks; intelligent road vehicles; obstacle recognition; real-time road recognition; traffic situation recognition; video camera; Cameras; Intelligent networks; Intelligent sensors; Intelligent vehicles; Knowledge representation; Neural networks; Real time systems; Road vehicles; Telecommunication traffic; Testing;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714133
