Trajectory-based Road Autolabeling with Lidar-Camera Fusion in Winter Conditions

TL;DR

elsarticle.cls addresses the need for a robust LaTeX class tailored to Elsevier submissions by reducing package conflicts and supporting multiple submission formats. It is built on the article class and integrates common packages such as natbib, geometry, graphicx, and hyperref, while offering streamlined handling of theorem environments. The class contributes by providing flexible preprint and final formats (model 1, 3, or 5), compatibility with AMS math packages, and clear installation guidance via CTAN and Elsevier resources. This reduces formatting friction and ensures consistent manuscript presentation across submission channels, improving the publication workflow for authors.

Abstract

Robust road segmentation in all road conditions is required for safe autonomous driving and advanced driver assistance systems. Supervised deep learning methods provide accurate road segmentation in the domain of their training data but cannot be trusted in out-of-distribution scenarios. Including the whole distribution in the trainset is challenging as each sample must be labeled by hand. Trajectory-based self-supervised methods offer a potential solution as they can learn from the traversed route without manual labels. However, existing trajectory-based methods use learning schemes that rely only on the camera or only on the lidar. In this paper, trajectory-based learning is implemented jointly with lidar and camera for increased performance. Our method outperforms recent standalone camera- and lidar-based methods when evaluated with a challenging winter driving dataset including countryside and suburb driving scenes. The source code is available at https://github.com/eerik98/lidar-camera-road-autolabeling.git