Title :
Vehicle Recognition Using Boosting Neural Network Classifiers
Author_Institution :
Inf. Eng. Coll., Central South Univ., Changsha
Abstract :
The paper describes a method for vehicle recognition using a generic shape model and boosting neural network classifiers. The generic shape model, which is able to represent different vehicle classes, is derived by principal component analysis on a set of training shapes recovered automatically from 2D image sequences. The pose parameters and the shape parameters of the model are estimated by fitting the model to the vehicle in each image using genetic algorithm, which are used to classify the vehicle. In order to improve the recognition accuracy and speed, we develop adaptive boosting neural network classifiers for vehicle recognition. Experiment results are presented for vehicle recognition, it is shown that our approach is more accuracy and faster than existing methods
Keywords :
genetic algorithms; image classification; image representation; image sequences; neural nets; object recognition; principal component analysis; stereo image processing; vehicles; 2D image sequences; adaptive boosting neural network classifiers; generic 3D shape model; genetic algorithm; pose parameter estimation; principal component analysis; shape parameter estimation; vehicle classification; vehicle recognition; vehicle representation; Adaptive systems; Automotive engineering; Boosting; Educational institutions; Genetic algorithms; Image recognition; Neural networks; Principal component analysis; Shape; Vehicle detection; Boosting Neural network classifiers; Boosting algorithm; Generic shape model; Vehicle recognition;
Conference_Titel :
Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
Conference_Location :
Dalian
Print_ISBN :
1-4244-0332-4
DOI :
10.1109/WCICA.2006.1713873