Neural Network Approach for the Identification System of the Type of Vehicle

TitreNeural Network Approach for the Identification System of the Type of Vehicle
Type de publicationCommunications avec actes
Année de publication2010
Titre de la Conférence/colloqueInternational Conference on Computational Intelligence and Communication Networks, CICN2010
Pagination162 - 166
Dates du congrès, colloque2010
Langueeng
Auteur(s)Daya, B., Akoum A. Hussain et Chauvet P.
Complément de titreInternational Conference on Computational Intelligence and Communication Networks, CICN2010
Université, organismeIEEE Computer Society
Ville, PaysBhopal
Numéro ISBN978-1-4244-8653-3 / 978-0-7695-4254-6
Mots-clésArtificial, Computational, Computer, geometrical, Multiclass, neural, traffic, type
Résumé

This paper represents a framework for multi-class vehicle type identification based on several geometrical parameters. The system of identification of object must thus have a very great adaptability. We represent a system of identification of the type (model) of vehicles per vision. Several geometrical parameters (distance, surface, ratio ...) of decision, on bases of images taken in real conditions, were tested and analyzed. The details of preprocessing as well as the features represented above are described in this paper. According to these parameters, the rate of identification can reach 95% on a basis of images made up of 9 classes of the type of vehicles. Then artificial neural network (ANNE) was used to verify and to classify the different types of the vehicles, and a ratio of identification of about 97% was obtained. The details of the implementation and results of the simulation are discussed in this paper.

Notes

Date du colloque : 11/2010

URLhttp://okina.univ-angers.fr/publications/ua1593
DOI10.1109/CICN.2010.42