Title :
A robust neural network multi-lane recognition system
Author :
Dawoud, Amer K. ; Foda, Salah G. ; Tolba, Ahmad S.
Author_Institution :
Dept. of Electr. & Comput. Eng., Kuwait Univ., Safat, Kuwait
fDate :
6/20/1905 12:00:00 AM
Abstract :
In this paper, the design and neural implementation of a vision based multi-lane highway lane recognition system are presented. The design objective of the system is to recognize the lane which a test vehicle is currently driving through by determining its left and right lane boundaries. When the proposed lane recognition system was tested it showed very high percentage of correct results in very difficult circumstances which suggests that it provides the basis for a reliable road following system
Keywords :
computer vision; computerised navigation; image recognition; neural nets; road vehicles; autonomous land vehicle; machine vision; multi-lane highway lane recognition system; navigation; road following system; road vehicle; robust neural network; Color; Image recognition; Matched filters; Navigation; Neural networks; Pixel; Road transportation; Road vehicles; System testing; Vehicle driving;
Conference_Titel :
Microelectronics, 1998. ICM '98. Proceedings of the Tenth International Conference on
Conference_Location :
Monastir
Print_ISBN :
0-7803-4969-5
DOI :
10.1109/ICM.1998.825594
