Road Detection through Supervised Classification

Abstract

Autonomous driving is a rapidly evolving technology. Autonomous vehicles are capable of sensing their environment and navigating without human input through sensory information such as radar, lidar, GNSS, vehicle odometry, and computer vision. This sensory input provides a rich dataset that can be used in combination with machine learning models to tackle multiple problems in supervised settings. In this paper we focus on road detection through gray-scale images as the sole sensory input. Our contributions are twofold: first, we introduce an annotated dataset of urban roads for machine learning tasks; second, we introduce a road detection framework on this dataset through supervised classification and hand-crafted feature vectors.

Wrong-Lane Accidents Detection using Random Forest Algorithm in comparison with Decision Tree for Improved Accuracy

“…It will increase visitors on one facet and hamper visitors greatly. It additionally will increase the opportunity of head-on collision in several instances (Alkhorshid et al 2016). About 355 humans die each 12 months because of the crashes in wrong-manner riding withinside the United States.…”

Recognition of sidewalk environment based on WideSegPlus

“…Therefore, it is not suitable for environment recognition for electric wheelchair automation. Another related study is roadway recognition [6][7][8][9]. However, the sidewalk is complicated in color and shape, the movement of people and bicycles on borders and obstacles is irregular.…”