Unthule: An Incremental Graph Construction Process for Robust Road Map Extraction from Aerial Images

The availability of highly accurate maps has become crucial due to the increasing importance of location-based mobile applications as well as autonomous vehicles. However, mapping roads is currently an expensive and humanintensive process. 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 [4, 10]. We show that these segmentation methods have high error rates (poor precision) because noisy CNN outputs are difficult to correct. We propose a novel approach, Unthule, to construct highly accurate road maps from aerial images. In contrast to prior work, Unthule uses an incremental search process guided by a CNN-based decision function to derive the road network graph directly from the output of the CNN. We train the CNN to output the direction of roads traversing a supplied point in the aerial imagery, and then use this CNN to incrementally construct the graph. We compare our approach with a segmentation method on fifteen cities, and find that Unthule has a 45% lower error rate in identifying junctions across these cities.