Road traffic signs guidance analysis for small navigation vehicle control system

This paper presents the road traffic signs detection and classification methods in vision-based robot guidance system that are applied for small navigation vehicle control system which can have two main roles that first for traffic signs detection and next for signs classification. Traffic signs recognition is a less studied field even though it provided road users with very valuable information about the road profiles in order to make running safer and easier. The algorithm are described in this paper take an advantage of sign features that their color and shapes are very different from natural environments. The systems are divided into three parts, first for detected and improved the quality of raw sign image. Second part for shape analysis with a continuous thinning algorithm and image encoding method, finally for the image recognition and decision by Fuzzy-Neural technique based on Back propagation Neural Network (BNN) model to display the right task. Some results from room experimental are shown here that show the system performance can work well but in real environmental scenes are valid to detect other kinds of signs that would train the mobile robot to perform some task at that place.