A fast fixed-point algorithm for independent component analysis
Neural Computation
Moving Target Classification and Tracking from Real-time Video
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
A Comparison of PCA and ICA for Object Recognition Under Varying Illumination
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Vehicle classification in distributed sensor networks
Journal of Parallel and Distributed Computing
A PCA-Based Vehicle Classification Framework
ICDEW '06 Proceedings of the 22nd International Conference on Data Engineering Workshops
IEEE Transactions on Intelligent Transportation Systems
Detection and classification of vehicles
IEEE Transactions on Intelligent Transportation Systems
IEEE Transactions on Intelligent Transportation Systems
Vehicle classification by acoustic signature
Mathematical and Computer Modelling: An International Journal
A neural-network appearance-based 3-D object recognition using independent component analysis
IEEE Transactions on Neural Networks
Bayesian multimodal fusion in forensic applications
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Shape Features of Overlapping Boundary for Classification of Moving Vehicles
International Journal of Computer Vision and Image Processing
Using adaptive background subtraction into a multi-level model for traffic surveillance
Integrated Computer-Aided Engineering
Hi-index | 0.00 |
This paper explores the computer vision based vehicle classification problem at a fine granularity. A framework is presented which incorporates various aspects of an Intelligent Transportation System towards vehicle classification. Given a traffic video sequence, the proposed framework first segments individual vehicles. Then vehicle segments are processed so that all vehicles are along the same direction and measured at the same scale. A filtering algorithm is applied to smooth the vehicle segment image. After these three steps of preprocessing, an ICA based algorithms is implemented to identify the features of each vehicle type. One-class SVM is used to categorize each vehicle into a certain class. Experimental results show the effectiveness of the framework.