OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction

TL;DR

OpenSatMap is a new high-resolution satellite dataset with detailed annotations, designed to improve large-scale map construction and autonomous driving applications.

Contribution

It introduces the first large-scale, fine-grained, high-resolution satellite dataset with instance-level annotations for map construction.

Findings

Largest dataset of its kind with high diversity

Provides a benchmark for satellite-based map construction

Aligns with popular autonomous driving datasets

Abstract

In this paper, we propose OpenSatMap, a fine-grained, high-resolution satellite dataset for large-scale map construction. Map construction is one of the foundations of the transportation industry, such as navigation and autonomous driving. Extracting road structures from satellite images is an efficient way to construct large-scale maps. However, existing satellite datasets provide only coarse semantic-level labels with a relatively low resolution (up to level 19), impeding the advancement of this field. In contrast, the proposed OpenSatMap (1) has fine-grained instance-level annotations; (2) consists of high-resolution images (level 20); (3) is currently the largest one of its kind; (4) collects data with high diversity. Moreover, OpenSatMap covers and aligns with the popular nuScenes dataset and Argoverse 2 dataset to potentially advance autonomous driving technologies. By publishing and maintaining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving.