Building Lane-Level Maps from Aerial Images

TL;DR

This paper introduces a large-scale aerial image dataset with high-quality lane annotations and a deep learning method, AerialLaneNet, for extracting detailed lane lines and their topology from aerial images, advancing high-definition mapping for autonomous driving.

Contribution

It provides the first large-scale aerial image dataset with detailed lane annotations and a novel two-stage deep learning approach for lane detection and topology extraction.

Findings

Significant improvement over state-of-the-art methods on the new dataset

Effective extraction of fine-grained lane lines with topology from aerial images

Availability of the dataset and code for further research

Abstract

Detecting lane lines from sensors is becoming an increasingly significant part of autonomous driving systems. However, less development has been made on high-definition lane-level mapping based on aerial images, which could automatically build and update offline maps for auto-driving systems. To this end, our work focuses on extracting fine-level detailed lane lines together with their topological structures. This task is challenging since it requires large amounts of data covering different lane types, terrain and regions. In this paper, we introduce for the first time a large-scale aerial image dataset built for lane detection, with high-quality polyline lane annotations on high-resolution images of around 80 kilometers of road. Moreover, we developed a baseline deep learning lane detection method from aerial images, called AerialLaneNet, consisting of two stages. The first stage is to produce coarse-grained results at point level, and the second stage exploits the coarse-grained results and feature to perform the vertex-matching task, producing fine-grained lanes with topology. The experiments show our approach achieves significant improvement compared with the state-of-the-art methods on our new dataset. Our code and new dataset are available at https://github.com/Jiawei-Yao0812/AerialLaneNet.