Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding
This addresses the challenge of automated road mapping for applications such as navigation and urban planning, representing an incremental advance by integrating existing approaches.
The paper tackles the problem of inferring road graphs from satellite imagery by proposing Sat2Graph, a method that combines segmentation and graph-based approaches using graph-tensor encoding, resulting in improved performance on TOPO and APLS metrics and the ability to infer stacked roads like overpasses.
Inferring road graphs from satellite imagery is a challenging computer vision task. Prior solutions fall into two categories: (1) pixel-wise segmentation-based approaches, which predict whether each pixel is on a road, and (2) graph-based approaches, which predict the road graph iteratively. We find that these two approaches have complementary strengths while suffering from their own inherent limitations. In this paper, we propose a new method, Sat2Graph, which combines the advantages of the two prior categories into a unified framework. The key idea in Sat2Graph is a novel encoding scheme, graph-tensor encoding (GTE), which encodes the road graph into a tensor representation. GTE makes it possible to train a simple, non-recurrent, supervised model to predict a rich set of features that capture the graph structure directly from an image. We evaluate Sat2Graph using two large datasets. We find that Sat2Graph surpasses prior methods on two widely used metrics, TOPO and APLS. Furthermore, whereas prior work only infers planar road graphs, our approach is capable of inferring stacked roads (e.g., overpasses), and does so robustly.