Multi-class Vehicle Type Recognition System
ANNPR '08 Proceedings of the 3rd IAPR workshop on Artificial Neural Networks in Pattern Recognition
Vehicle make & model identification using scale invariant transforms
VIIP '07 The Seventh IASTED International Conference on Visualization, Imaging and Image Processing
An approach for moving object recognition based on BPR and CI
Information Systems Frontiers
| Hi-index | 0.00 |
We describe a system for automatic recognition of verhicle type (make and model) from frontal views, aimed at secure access, surveillance and traffic monitoring applications. The system extracts gradient features from reference patches in images of car fronts and performs recognition in two stages.In the first stage gradient based feature vectors are used to produce a ranked list of possible candidate classes.The result is then refined by using a novel match refinement algorithm that maximizes the discrimination between the subset of most likely classes by optimising for objectpose and adaptively normalising feature vectors.We test the system on over 1000 images containing 77 difference vehicle classes, and demonstrate that such a system can provide reliable verification (EER