Driving Safe Speed Estimation Based on Outside Environment Vision Analysis

Abstract

Using predefined speed limits on roads had huge positive safety effects on decreasing the vehicle accident rate. On the other hand using these static limits was the 20th-century solution. With the recent evolution of machine learning, driver assistant systems, and autonomous driving the necessity for dynamic speed limits are raised. In this paper we propose a novel method to analyze the scene and adjust the speed limits according to the environment's dynamic changes taking into account static constraints. Our proposed system is a recommendation system to estimate safe speed limits. It will consider the static predefined speed limits as well as other values like (the number of vehicles on the scene, the relative distance to the closest vehicle, the road width and curvature, the weather state, and the day/night (illumination) states.

Keywords

• safe speed estimation
• driver monitoring
• inteloignet transportation system