Detecting Driveable Area for Autonomous Vehicles

TL;DR

This paper explores using Mask R-CNN on the BDD100k dataset to detect driveable areas and differentiate lanes, aiding autonomous vehicle decision-making.

Contribution

It demonstrates the feasibility of deep learning for driveable area recognition and lane differentiation in autonomous driving.

Findings

Mask R-CNN successfully identifies driveable regions

Differentiates between current and alternative lanes

Shows potential for real-time autonomous driving applications

Abstract

Autonomous driving is a challenging problem where there is currently an intense focus on research and development. Human drivers are forced to make thousands of complex decisions in a short amount of time,quickly processing their surroundings and moving factors. One of these aspects, recognizing regions on the road that are driveable is vital to the success of any autonomous system. This problem can be addressed with deep learning framed as a region proposal problem. Utilizing a Mask R-CNN trained on the Berkeley Deep Drive (BDD100k) dataset, we aim to see if recognizing driveable areas, while also differentiating between the car's direct (current) lane and alternative lanes is feasible.