Streetwise: Mapping Citizens' Perceived Spatial Qualities

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 well as a group of humans.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  J. C. Dunn,et al.  A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters , 1973 .

[3]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[4]  M Sawada,et al.  Deep mapping gentrification in a large Canadian city using deep learning and Google Street View , 2019, PloS one.

[5]  Reza Zafarani,et al.  Maximizing benefits from crowdsourced data , 2012, Computational and Mathematical Organization Theory.

[6]  Keiron O'Shea,et al.  An Introduction to Convolutional Neural Networks , 2015, ArXiv.

[7]  Tobias Preis,et al.  Using deep learning to quantify the beauty of outdoor places , 2017, Royal Society Open Science.

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Tom Minka,et al.  TrueSkillTM: A Bayesian Skill Rating System , 2006, NIPS.

[10]  Travis C. Pratt,et al.  Revisiting Broken Windows Theory: Examining the Sources of the Discriminant Validity of Perceived Disorder and Crime , 2010 .

[11]  Fernando González-Ladrón-de-Guevara,et al.  Towards an integrated crowdsourcing definition , 2012, J. Inf. Sci..

[12]  Daniel D. Dilks,et al.  “Referred Visual Sensations”: Rapid Perceptual Elongation after Visual Cortical Deprivation , 2009, The Journal of Neuroscience.

[13]  Kevin Lynch,et al.  The Image of the City , 1960 .

[14]  Ramesh Raskar,et al.  Deep Learning the City: Quantifying Urban Perception at a Global Scale , 2016, ECCV.

[15]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[16]  Tareq Abed Mohammed,et al.  Understanding of a convolutional neural network , 2017, 2017 International Conference on Engineering and Technology (ICET).

[17]  Alexei A. Efros,et al.  The Unreasonable Effectiveness of Deep Features as a Perceptual Metric , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Prabhat,et al.  Artificial Neural Network , 2018, Encyclopedia of GIS.

[19]  Hui Wang,et al.  A machine learning-based method for the large-scale evaluation of the qualities of the urban environment , 2017, Comput. Environ. Urban Syst..

[20]  Ivana Čermáková,et al.  The synergy of linguistic summaries, fuzzy functional dependencies and land coverings for augmenting informativeness in smart cities , 2020, 2020 28th Telecommunications Forum (TELFOR).

[21]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[22]  César A. Hidalgo,et al.  The Collaborative Image of The City: Mapping the Inequality of Urban Perception , 2013, PloS one.