Annotation-Free Detection of Drivable Areas and Curbs Leveraging LiDAR Point Cloud Maps

TL;DR

This paper introduces MADL, a LiDAR-based automatic data labeling system for drivable area and curb detection that improves training data quality and enhances perception accuracy in autonomous driving.

Contribution

The paper presents a novel map-based automatic data labeler (MADL) that leverages LiDAR mapping to generate large-scale, accurate training datasets without manual labeling.

Findings

MADL outperforms traditional labeling methods in accuracy and robustness.

Experiments show MADL achieves comparable or better performance than manual labels.

The approach effectively addresses occlusion and sparsity issues in LiDAR data.

Abstract

Drivable areas and curbs are critical traffic elements for autonomous driving, forming essential components of the vehicle visual perception system and ensuring driving safety. Deep neural networks (DNNs) have significantly improved perception performance for drivable area and curb detection, but most DNN-based methods rely on large manually labeled datasets, which are costly, time-consuming, and expert-dependent, limiting their real-world application. Thus, we developed an automated training data generation module. Our previous work generated training labels using single-frame LiDAR and RGB data, suffering from occlusion and distant point cloud sparsity. In this paper, we propose a novel map-based automatic data labeler (MADL) module, combining LiDAR mapping/localization with curb detection to automatically generate training data for both tasks. MADL avoids occlusion and point cloud sparsity issues via LiDAR mapping, creating accurate large-scale datasets for DNN training. In addition, we construct a data review agent to filter the data generated by the MADL module, eliminating low-quality samples. Experiments on the KITTI, KITTI-CARLA and 3D-Curb datasets show that MADL achieves impressive performance compared to manual labeling, and outperforms traditional and state-of-the-art self-supervised methods in robustness and accuracy.