This paper tackles the task of estimating the topology of road networks from aerial images. Building on top of a global model that performs a dense semantical classification of the pixels of the image, we design a Convolutional Neural Network (CNN) that predicts the local connectivity among the central pixel of an input patch and its border points. By iterating this local connectivity we sweep the whole image and infer the global topology of the road network, inspired by a human delineating a complex network with the tip of their finger. We perform an extensive and comprehensive qualitative and quantitative evaluation on the road network estimation task, and show that our method also generalizes well when moving to networks of retinal vessels.
@article{arxiv.1808.09814,
title = {Iterative Deep Learning for Road Topology Extraction},
author = {Carles Ventura and Jordi Pont-Tuset and Sergi Caelles and Kevis-Kokitsi Maninis and Luc Van Gool},
journal= {arXiv preprint arXiv:1808.09814},
year = {2018}
}
Comments
BMVC 2018 camera ready. Code: https://github.com/carlesventura/iterative-deep-learning. arXiv admin note: substantial text overlap with arXiv:1712.01217