A Smart System for Detection of Road Lane and Divider

Abstract

Road Lane and divider detection is a core part in environmental perception for driver assistance system. The paper discusses about machine learning and computer vision approach to identify road lanes and dividers and proposes a system for detection of road lane and divider. Driving assistance systems heavily rely on the road lane and divider recognition. Voting classification was implemented using 7 different classifiers. The combination of Scale Invariant Feature Transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) provided feature extraction. Principle Component Analysis (PCA) provided dimension reduction. The performance has been examined on the basis of accuracy (95.50%), precision (78.81%), recall (65.71%), and F1 score (71.67%). The proposed solution is helpful in solving issues related to road safety and reducing road accidents.