Detecting and Tracking a Road-Drivable Area with Three-Dimensional Point Clouds and IoT for Autonomous Applications

This work presents a Light Detection and Ranging (LiDAR)-based point cloud method for detecting and tracking road edges. Initially, this work explores the progress in detecting road curb issues. A dataset (called PandaSet) with a Pandar64 sensor to capture different city scenes is used. LiDAR point cloud, as part of an IoT ecosystem, detects the road curb and requires distinguishing the right and left road curbs with regard to the ego car. The curb point’s features use Random Sample Consensus (RANSAC)-based polynomial quadratic approximation to obtain the prospect curb points to eliminate false positive ones. Through extensive experiments, we demonstrate the effectiveness and reliability of our method under various traffic and environmental conditions. Our results showcase a maximum drift of 1.62 m for left curb points and 0.87 m for right curb points, highlighting the superior accuracy and stability of our approach. This LiDAR-based curb detection framework paves the way for enhanced lane recognition and path planning in autonomous driving applications.