RNGDet: Road Network Graph Detection by Transformer in Aerial Images

by   Zhenhua Xu, et al.

Road network graphs provide critical information for autonomous vehicle applications, such as motion planning on drivable areas. However, manually annotating road network graphs is inefficient and labor-intensive. Automatically detecting road network graphs could alleviate this issue, but existing works are either segmentation-based approaches that could not ensure satisfactory topology correctness, or graph-based approaches that could not present precise enough detection results. To provide a solution to these problems, we propose a novel approach based on transformer and imitation learning named RNGDet (Road Network Graph Detection by Transformer) in this paper. In view of that high-resolution aerial images could be easily accessed all over the world nowadays, we make use of aerial images in our approach. Taken as input an aerial image, our approach iteratively generates road network graphs vertex-by-vertex. Our approach can handle complicated intersection points of various numbers of road segments. We evaluate our approach on a publicly available dataset. The superiority of our approach is demonstrated through the comparative experiments.


page 1

page 4

page 5

page 6

page 8

page 10


iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving

Detection of road curbs is an essential capability for autonomous drivin...

Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving

Road-boundary detection is important for autonomous driving. For example...

Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding

Inferring road graphs from satellite imagery is a challenging computer v...

Discovery of Important Crossroads in Road Network using Massive Taxi Trajectories

A major problem in road network analysis is discovery of important cross...

csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps

High-Definition (HD) maps can provide precise geometric and semantic inf...

Image-Conditioned Graph Generation for Road Network Extraction

Deep generative models for graphs have shown great promise in the area o...