The Similarity of European Cities Based on Image Analysis

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15310%2F19%3A73601789" target="_blank" >RIV/61989592:15310/19:73601789 - isvavai.cz</a>
Result on the web
<a href="https://obd.upol.cz/id_publ/333181675" target="_blank" >https://obd.upol.cz/id_publ/333181675</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-30329-7_31" target="_blank" >10.1007/978-3-030-30329-7_31</a>

Result language
angličtina
Original language name
The Similarity of European Cities Based on Image Analysis
Original language description
This article presents the finding of similar cities in Europe from data set Urban Atlas. Basic categories of landuse describe each city. One hundred cites were selected as a basic data set according to size. For finding the similarity, the trained neural network was used. A neural network is part of embedded add-ins Image Analytics in Orange software. One embedder in Orange was selected for the presented purpose. Finally, the hierarchical clustering was used for image descriptors received form neural networks. As a result, the couples of most similar cities is presented in the article. The cities are similar according to the patterns of urban fabrics or green areas patterns or shapes of some areas.
Czech name
—
Czech description
—

Project
<a href="/en/project/EE2.3.20.0170" target="_blank" >EE2.3.20.0170: Building of Research Team in the Field of Environmental Modeling and the Use of Geoinformation Systems with the Consequence in Participation in International Networks and Programs</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)