For best experience please turn on javascript and use a modern browser!
You are using a browser that is no longer supported by Microsoft. Please upgrade your browser. The site may not present itself correctly if you continue browsing.

With Google Streetview and Deep Learning, researchers at the University of Amsterdam and the University of Twente identified how the urban environment is linked to the vitality of social organisations and neighbourhoods. They conclude that, if an environment provides more space to pedestrians, this will be conducive to neighbourhood-based social organisations’ chances of survival.

Neighbourhood-based social organisations are important building blocks for social life in urban districts. They play a central role in representing, connecting, empowering and mobilising district residents and hence in promoting social interactions and mutual solidarity. Examples are organisations that organise sports activities, hobby clubs and cultural associations. The absence of these organisations undermines social integration in a district and may even cause or exacerbate problems among residents. This applies in particular to poor, isolated or marginalised districts, where residents often lack the means to galvanise social life. Earlier studies have shown, for instance, that community organisations are essential in rebuilding areas following natural disasters, such as hurricanes.

An example of Google Street View (GSV) panorama segmentation by  DeepLabv3+: a) original GSV panorama and b) segmented image.
An example of Google Street View (GSV) panorama segmentation by DeepLabv3+: a) original GSV panorama and b) segmented image.

Analyses using Deep Learning and Google Street View

Political scientist Floris Vermeulen (University of Amsterdam) and urban geographer Mingshu Wang (University of Twente) researched the vitality of social organisations in Amsterdam. They specifically examined the role of the urban environment in this. To that end, they used Google Street View (GSV) to identify where and in what kind of environment social organisations are located and machine learning or deep learning to automatically retrieve certain characteristics of the urban environment from street views, such as the number of vehicles and pavement space. There were able to establish a connection between vehicle, pedestrian or mixed-oriented environments and the continued existence of community organisations.

Pedestrian-friendly environment has the most positive effect

Vermeulen and Wang conclude that urban environments that encourage people to walk considerably increase social organisations’ chances of survival. Walking makes it easier for neighbourhood residents to make contact and meet each other on the street. This helps to strengthen the community function of a social organisation and has positive consequences for social life in the neighbourhood. However, in areas where walking was discouraged as a result of promoting the intense use of cars, the vitality of social organisations diminished. Mixed infrastructure, targeted at both pedestrians and vehicles, also proved to have a positive, although less strong, effect on the chances of survival of community organisations.

‘This study highlights the need for urban planners and local policymakers to fully incorporate pedestrians in their designs. Pedestrians can help to maintain the vibrancy of a city in perhaps unexpected ways,’ according to Vermeulen and Wang.

Publication details

Mingshu Wang en Floris Vermeulen (2020), ‘Life between buildings from a street view image: What do big data analytics reveal about neighbourhood organisational vitality?’, Urban Studies, DOI: 10.1177/0042098020957198

Dr. F.F. (Floris) Vermeulen

Faculty of Social and Behavioural Sciences

Programme group: Challenges to Democratic Representation