Iterative Deep Learning for Road Topology Extraction

08/28/2018
by   Carles Ventura, et al.
0

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.

READ FULL TEXT
research
12/04/2017

Iterative Deep Learning for Network Topology Extraction

This paper tackles the task of estimating the topology of filamentary ne...
research
07/17/2020

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Most state-of-the-art approaches to road extraction from aerial images r...
research
12/19/2021

Topology Preserving Local Road Network Estimation from Single Onboard Camera Image

Knowledge of the road network topology is crucial for autonomous plannin...
research
09/15/2020

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

We propose a novel, connectivity-oriented loss function for training dee...
research
06/23/2021

Communication in Complex Networks

The investigation of properties of networks has many applications and is...
research
02/11/2018

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 i...
research
01/10/2022

Swin transformers make strong contextual encoders for VHR image road extraction

Significant progress has been made in automatic road extra-ction or segm...

Please sign up or login with your details

Forgot password? Click here to reset