A New Vehicle Recognition Approach Based on Graph Spectral Theory and BP Neural Network

Author

Yu, Wang ; Lei, Li ; Feng, ShiJian

Author_Institution

Nanjing Artillery Acad. of PL A, Langfang, China

Volume

2

fYear

2012

fDate

23-25 March 2012

Firstpage

84

Lastpage

86

Abstract

A new vehicle recognition approach based on graph spectral theory and neural networks is proposed in this paper. In the approach, image threshold method based on graph spectral theory is used for image preprocessing. And after filter of undetermined regions with rules, regions left are gray-unified. These gray values are input into neural network to recognize vehicle and vehicle types. The experiment proves that this method has high recognition rate and low false rate.

Keywords

backpropagation; graph theory; neural nets; object recognition; road traffic; traffic engineering computing; BP neural network; backpropagation; false rate; graph spectral theory; gray-unified image; image preprocessing; image threshold method; recognition rate; vehicle recognition approach; vehicle type recognition; Feature extraction; Image recognition; Learning systems; Neural networks; Satellites; Vehicle detection; Vehicles; Graph Spectral Theory; Neural Network; Vehicle Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Electronics Engineering (ICCSEE), 2012 International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-1-4673-0689-8

Type

conf

DOI

10.1109/ICCSEE.2012.116

Filename

6187970