RoadTracer: Automatic Extraction of Road Networks from Aerial Images

By Favyen Bastani, Songtao He, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Samuel Madden, David J. DeWitt. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

371 citations recorded by the source corpus.

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.

Subfields: Ecology, Environmental Engineering, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/82d66fa2666e3e8798085fdc0155e6b45b707f32

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Ocean Engineering

Citations in the corpus

Satlas: A Large-Scale, Multi-Task Dataset for Remote Sensing Image Understanding (2022, methodology): “ized polyline extraction architectures have been shown to improve accuracy [9, 30, 49], we opt to employ the simpler segmentation approach [56] where we apply the UNet head to segment images for polyline categories, and postprocess the segmentation probabilities with binary thresholding, morphologic”
Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery (2020, methodology): “road or building), there were many improved techniques [2, 15, 3] for its application scenario.”
Topological Map Extraction From Overhead Images (2018, methodology): “We compare the results of our method to the state-of-the-art methods DeepRoadMapper [32] and RoadTracer [4].”
MP3: A Unified Model to Map, Perceive, Predict and Plan (2021, background): “Online Mapping: While there are many ofﬂine mapping approaches [4, 22, 33], these rely on satellite imagery or multiple passes through the same scene with a data collection vehicle to gather dense information, and often involve a human-in-the-loop.”
D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction (2018, methodology): “Most of these methods can be seperated into three categories: generating pixel-level labeling of roads [1, 2], detecting skeletons of roads [3, 4] and a combination of both [5, 6].”
Self-Driving Cars: A Survey (2019, methodology): “[BAS18] propose the Road Tracer method that seeks to produce the road map directly from the CNN, rather than relying on intermediate image representations.”