Title :
Study on blurry and smudgy path recognition by fuzzy neural network
Author :
Wang, Rongben ; Ji, Shouwen ; Wang, Zhizhong ; Guo, Keyou
Author_Institution :
Transp. of Coll., Jilin Univ., Changchun, China
Abstract :
The methods of recognizing blurry and smudgy navigation path are studied by using fuzzy neural network for JLUIV-2 vision navigation intelligent vehicle. Two fuzzy neural network models are developed, one model has 5 layers, and uses normal distribution probability function as its fuzzy function, another model has 6 layers, and uses π function as its fuzzy function. The dynamic BP algorithm is used to train the two fuzzy neural networks. Experiments of the path recognizing and practical autonomous navigation are done by using JLUIV-2 intelligent vehicle. The results show that the two fuzzy neural networks can effectively recognize the blurry and smudgy navigation path.
Keywords :
backpropagation; computer vision; driver information systems; fuzzy neural nets; image recognition; probability; road vehicles; JLUIV-2 vision navigation intelligent vehicle; backpropagation; blurry path recognition; dynamic BP algorithm; fuzzy neural network; fuzzy neural network models; normal distribution probability function; smudgy path recognition; Artificial neural networks; Automatic control; Charge coupled devices; Fuzzy neural networks; Gaussian distribution; Image recognition; Intelligent vehicles; Navigation; Neural networks; Pixel;
Conference_Titel :
Intelligent Vehicle Symposium, 2002. IEEE
Print_ISBN :
0-7803-7346-4
DOI :
10.1109/IVS.2002.1187945
