Circular road signs recognition with soft classifiers
Integrated Computer-Aided Engineering - Artificial Neural Networks
Intelligent System for Traffic Signs Recognition in Moving Vehicles
IEA/AIE '08 Proceedings of the 21st international conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems: New Frontiers in Applied Artificial Intelligence
Real-Time Road Signs Tracking with the Fuzzy Continuously Adaptive Mean Shift Algorithm
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Generation of Training Data by Degradation Models for Traffic Sign Symbol Recognition
IEICE - Transactions on Information and Systems
Traffic sign recognition using evolutionary adaboost detection and forest-ECOC classification
IEEE Transactions on Intelligent Transportation Systems
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
An optimization on pictogram identification for the road-sign recognition task using SVMs
Computer Vision and Image Understanding
Traffic sign recognition using discriminative local features
IDA'07 Proceedings of the 7th international conference on Intelligent data analysis
Road-signs recognition system for intelligent vehicles
RobVis'08 Proceedings of the 2nd international conference on Robot vision
Traffic scene segmentation and robust filtering for road signs recognition
ICCVG'10 Proceedings of the 2010 international conference on Computer vision and graphics: Part I
Robust class similarity measure for traffic sign recognition
IEEE Transactions on Intelligent Transportation Systems
Structural inference of sensor-based measurements
SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Neural network based smart vision system for driver assistance in extracting traffic signposts
Proceedings of the CUBE International Information Technology Conference
Hi-index | 0.00 |
Deriving an informative data representation is an important prerequisite when designing road-sign classifiers. A frequently used strategy for road-sign classification is based on the normalized cross correlation similarity to class prototypes followed by the nearest neighbor classifier. Because of the global nature of the cross correlation similarity, this method suffers from presence of uninformative pixels (caused, e.g., by occlusions) and is computationally demanding. In this paper, a novel concept of a trainable similarity measure is introduced, which alleviates these shortcomings. The similarity is based on individual matches in a set of local image regions. The set of regions that are relevant for a particular similarity assessment is refined by the training process. It is illustrated on a set of experiments with road-sign-classification problems that the trainable similarity yields high-performance data representations and classifiers. Apart from a multiclass classification accuracy, nonsign rejection capability and computational demands in execution are also discussed. It appears that the trainable similarity representation alleviates some difficulties of other algorithms that are currently used in road-sign classification