A Comprehensive Real-Time Road-Lanes Tracking Technique for Autonomous Driving

Abstract

In this paper, an advanced-and-reliable road-lanes detection and tracking solution is proposed and implemented. The proposed solution is well suited for use in Advanced Driving Assistance Systems (ADAS) or Self-Driving Cars (SDC). The main emphasis of the proposed solution is the precision and the predictability in identifying the driving-lane boundaries (linear or curved) and tracking it throughout the drive. Moreover, the solution provides fast enough computation to be embedded in affordable CPUs that are employed by ADAS systems. The proposed solution is mainly a pipeline of reliable computer-vision algorithms that augment each other and take in raw RGB images to produce the required lane boundaries that represent the front driving space for the car. The main contribution of this paper is the precise fusion of the employed algorithms where some of them work in parallel to strengthen each other in order to produce a sophisticated real-time output. Each used algorithm is described in detail, implemented and its performance is evaluated using actual road images and videos captured by the front-mounted camera of the car. The whole pipeline performance is also tested and evaluated on real videos. The evaluation of the proposed solution shows that it reliably detects and tracks road boundaries under various conditions.