Authors:
Moreno Colombo
1
;
Jhonny Pincay
1
;
Oleg Lavrovsky
2
;
Laura Iseli
3
;
Joris Van Wezemael
3
;
4
and
Edy Portmann
1
Affiliations:
1
Human-IST Institute, University of Fribourg, Boulevard de Pérolles 90, Fribourg, Switzerland
;
2
Datalets, Könizstrasse 298, Köniz, Switzerland
;
3
IVO Innenentwicklung, Sternmattstrasse 3, Luzern, Switzerland
;
4
Institute for Spatial and Landscape Development, ETH Zurich, Stefano-Franscini-Platz 5, 8093 Zürich, Switzerland
Keyword(s):
Smart Citizens, Smart City, Crowdsourcing, Neural Networks.
Abstract:
Streetwise is the first map of spatial quality of urban design of Switzerland. Streetwise measures the human perception of spatial situations and uses crowdsourcing methods for this purpose: a large number of people are shown pairs of street-level images of public space online; by clicking on an image, they each give an evaluation about the place they consider has a better atmosphere, which is the focus of this article. With the gathered data, a machine learning model was trained, which allowed learning features that motivate people to choose one image over another. The trained model was then used to estimate a score representing the perceived atmosphere in a large number of images from different urban areas within the Zurich metropolitan region, which could then be visualized on a map to offer a comprehensive overview of the atmosphere of the analyzed cities. The accuracy obtained from the evaluation of the machine learning model indicates that the method followed can perform as wel
l as a group of humans.
(More)