Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method

TL;DR

This paper introduces a large-scale global satellite road dataset and a novel extraction model, SAM-Road++, that improves accuracy and robustness in road graph extraction for autonomous navigation.

Contribution

It provides the first large-scale global dataset for satellite road graph extraction and proposes a new model with a node-guided resampling and extended-line strategy.

Findings

The dataset is 20 times larger than existing datasets.

SAM-Road++ outperforms previous models in unseen regions.

The proposed methods effectively mitigate occlusion and training-inference mismatch.

Abstract

Recently, road graph extraction has garnered increasing attention due to its crucial role in autonomous driving, navigation, etc. However, accurately and efficiently extracting road graphs remains a persistent challenge, primarily due to the severe scarcity of labeled data. To address this limitation, we collect a global-scale satellite road graph extraction dataset, i.e. Global-Scale dataset. Specifically, the Global-Scale dataset is $\sim20 \times$ larger than the largest existing public road extraction dataset and spans over 13,800 $km^2$ globally. Additionally, we develop a novel road graph extraction model, i.e. SAM-Road++, which adopts a node-guided resampling method to alleviate the mismatch issue between training and inference in SAM-Road, a pioneering state-of-the-art road graph extraction model. Furthermore, we propose a simple yet effective ``extended-line'' strategy in SAM-Road++ to mitigate the occlusion issue on the road. Extensive experiments demonstrate the validity of the collected Global-Scale dataset and the proposed SAM-Road++ method, particularly highlighting its superior predictive power in unseen regions. The dataset and code are available at \url{https://github.com/earth-insights/samroadplus}.