DeepAerialMapper: Deep Learning-based Semi-automatic HD Map Creation for Highly Automated Vehicles

TL;DR

DeepAerialMapper introduces a semi-automatic deep learning approach to generate high-definition maps from aerial imagery, significantly reducing manual effort and achieving over 96% accuracy in lane and border detection.

Contribution

The paper presents a novel semi-automatic method using neural networks for HD map creation from aerial images, including a new dataset and a pipeline that outputs maps compatible with standard tools.

Findings

Achieved over 96% recall and precision in lane and border detection.

Developed a publicly available dataset of aerial images for urban roads in Germany.

Created a pipeline that produces maps in Lanelet2 format for easy extension.

Abstract

High-definition maps (HD maps) play a crucial role in the development, safety validation, and operation of highly automated vehicles. Efficiently collecting up-to-date sensor data from road segments and obtaining accurate maps from these are key challenges in HD map creation. Commonly used methods, such as dedicated measurement vehicles and crowd-sourced data from series vehicles, often face limitations in commercial viability. Although high-resolution aerial imagery offers a cost-effective or even free alternative, it requires significant manual effort and time to transform it into maps. In this paper, we introduce a semi-automatic method for creating HD maps from high-resolution aerial imagery. Our method involves training neural networks to semantically segment aerial images into classes relevant to HD maps. The resulting segmentation is then hierarchically post-processed to generate a prototypical HD map of visible road elements. Exporting the map to the Lanelet2 format allows easy extension for different use cases using standard tools. To train and evaluate our method, we created a dataset using public aerial imagery of urban road segments in Germany. In our evaluation, we achieved an automatic mapping of lane markings and road borders with a recall and precision exceeding 96%. The source code for our method is publicly available at https://github.com/RobertKrajewski/DeepAerialMapper.