RoadTracer: Automatic Extraction of Road Networks from Aerial Images

TL;DR

RoadTracer is a novel method that automatically constructs accurate road network maps from aerial images by iteratively guiding a graph search with a CNN-based decision function, outperforming segmentation-based approaches.

Contribution

It introduces an iterative search approach guided by CNN decisions to directly infer road graphs, reducing errors compared to segmentation methods.

Findings

RoadTracer captures 45% more junctions at 5% error rate across fifteen cities.

It outperforms traditional segmentation methods in accuracy.

The approach effectively constructs road networks from aerial imagery.

Abstract

Mapping road networks is currently both expensive and labor-intensive. High-resolution aerial imagery provides a promising avenue to automatically infer a road network. Prior work uses convolutional neural networks (CNNs) to detect which pixels belong to a road (segmentation), and then uses complex post-processing heuristics to infer graph connectivity. We show that these segmentation methods have high error rates because noisy CNN outputs are difficult to correct. We propose RoadTracer, a new method to automatically construct accurate road network maps from aerial images. RoadTracer uses an iterative search process guided by a CNN-based decision function to derive the road network graph directly from the output of the CNN. We compare our approach with a segmentation method on fifteen cities, and find that at a 5% error rate, RoadTracer correctly captures 45% more junctions across these cities.