English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic Extraction of road network from satellite images is a goal that canbenefit and even enable new technologies. Methods that combine machine learning(ML) and computer vision have been proposed in recent years which make the tasksemi-automatic by requiring the user to provide curated training samples. Theprocess can be fully automatized if training samples can be producedalgorithmically. Of course, this requires a robust algorithm that canreconstruct the road networks from satellite images reliably so that the outputcan be fed as training samples. In this work, we develop such a technique byinfusing a persistence-guided discrete Morse based graph reconstructionalgorithm into ML framework.  We elucidate our contributions in two phases. First, in a semi-automaticframework, we combine a discrete-Morse based graph reconstruction algorithmwith an existing CNN framework to segment input satellite images. We show thatthis leads to reconstructions with better connectivity and less noise. Next, ina fully automatic framework, we leverage the power of the discrete-Morse basedgraph reconstruction algorithm to train a CNN from a collection of imageswithout labelled data and use the same algorithm to produce the final outputfrom the segmented images created by the trained CNN. We apply thediscrete-Morse based graph reconstruction algorithm iteratively to improve theaccuracy of the CNN. We show promising experimental results of this newframework on datasets from SpaceNet Challenge.

Road Network Reconstruction from Satellite Images with Machine Learning Supported by Topological Methods