Recognition of the Type of Vehicle and the Road Obstacle in Optimized HRWD-PNN based Image Processing System

The automatic recognition of the type of the vehicle constitutes one of the contemporary means used for monitoring of the road transport. The paper presents an application of neural network in a hybrid, high speed, pattern recognition system applied to the recognition of road vehicles. The paper considers also an application of the infrared imaging in the problems of recognition of the type of obstacle present on the road during the foggy conditions. The feature extraction part of the system used for both purposes is built as a holographic ring wedge detector and the classifier is a probabilistic neural network. Since the feature extractor can be produced with relatively low costs from computer generated high resolution masks, such masks should be designed specifically to given recognition task. This requires automatic knowledge acquisition and processing with the goal of optimization of the feature space dedicated for subsequent use of neural network based classifier. We present also the experimental results obtained by computer simulation of the optimized systems applied in both recognition areas. Key-Words: hybrid systems, neural networks, rough sets, holographic ring-wedge detectors, image processing, pattern recognition, infrared imaging