NARMA-L2 Neuro controller for speed regulation of an intelligent vehicle based on image processing techniques

Abstract

In order to be deployed in driving environments, intelligent transport system (ITS) must be able to recognize and respond to exceptional road conditions such as traffic signs, highway work zones and imminent road works automatically. This research presents a new vehicle speed control approach based on image processing technique. It aims to firstly recognize the road sign image and then, send the recognized speed as reference to the control unit. Obviously, recognition of traffic sign is playing a vital role in the intelligent transport system, it enhances traffic safety by providing drivers with safety and precaution information about road hazards. To recognize the traffic sign, an image processing unit ensured 3 steps: traffic board detection, feature extraction and sign classification. The detection phase is based on morphological operations, thresholding and contrast analysis. Steerable filters based technique was adopted to extract features from the segmented sign images. Finally, traffic signs classification is done by an intelligent Bayesian Regularization Neural Network (BRNN). It achieves a classification accuracy up to 97%. Once recognized, the resulting speed is taken as reference of the NARMA-L2 based control unit to regulate the speed of a DC motor. The simulation results show that our speed vehicle is controlled successfully with different speed references