An Enhanced Artificial Intelligence-Based Approach Applied to Vehicular Traffic Signs Detection and Road Safety Enhancement
Anass Barodi, Abderrahim Bajit, Taoufiq El Harrouti, Ahmed Tamtaoui, Mohammed Benbrahim
Abstract
The paper treats a problem for detection and recognition objects in computer vision sector, where researchers recommended OpenCV software and development tool, it's several and better-remembered library resource for isolating, detecting, and recognition of particular objects, what we would find an appropriate system for detecting and recognition traffic roads signs. The robustness with optimization is a necessary element in the computer vision algorithms, we can find a very large number of technics in object detection, for example, shapes transformation, color selection, a region of interest ROI, and edge detection, combined all these technics to reach high precision in animated video or still image processing. The system we are trying to develop, is in high demand in the automotive sector such as intelligent vehicles or autonomous driving assist systems ADAS, based on intelligent recognition, applying Artificial Intelligence, by using Deep Learning, exactly Convolutional Neural Network (CNN) architecture, our system improves the high accuracy of detection and recognition of traffic road signs with lower loss.