Deep mapping gentrification in a large Canadian city using deep learning and Google Street View

Abstract

Gentrification is multidimensional and complex, but there is general agreement that visible changes to neighbourhoods are a clear manifestation of the process. Recent advances in computer vision and deep learning provide a unique opportunity to support automated mapping or ‘deep mapping’ of perceptual environmental attributes. We present a Siamese convolutional neural network (SCNN) that automatically detects gentrification-like visual changes in temporal sequences of Google Street View (GSV) images. Our SCNN achieves 95.6% test accuracy and is subsequently applied to GSV sequences at 86110 individual properties over a 9-year period in Ottawa, Canada. We use Kernel Density Estimation (KDE) to produce maps that illustrate where the spatial concentration of visual property improvements was highest within the study area at different times from 2007–2016. We find strong concordance between the mapped SCNN results and the spatial distribution of building permits in the City of Ottawa from 2011 to 2016. Our mapped results confirm those urban areas that are known to be undergoing gentrification as well as revealing areas undergoing gentrification that were previously unknown. Our approach differs from previous works because we examine the atomic unit of gentrification, namely, the individual property, for visual property improvements over time and we rely on KDE to describe regions of high spatial intensity that are indicative of gentrification processes.

Measuring and mapping displacement: The problem of quantification in the battle against gentrification

“…Even in these cases, changes at the micro level of blocks and streets appear best ground-truthed by local experts. Given the risk of mis-identifying neighbourhoods as gentrifying, this seems to be an essential part of the analytical process, although novel use of digital data products such as Google Street View offers a less labour-intensive alternative (see, for example, Hwang and Sampson, 2014, and Ilic et al, 2019, on using deep learning computer-based vision techniques). Ultimately, visual proxies like the make and age of cars on a given street may not be the best identifier of gentrification, but the ability to automatically analyse large numbers of images compiled over a number of years seems to offer an efficient means of registering where socio-economic change is occurring.…”

Quantifying the Characteristics of the Local Urban Environment through Geotagged Flickr Photographs and Image Recognition

“…These results also illustrate how urban perception changes over time, showing that dynamic analytics are important for the urban environment. These bridge the identified research gap in the dynamic features of cities [10,36]. Meanwhile, the practical implications of the dynamic characteristics of UAOIs can be reflected in the actions of retailers and local authorities.…”

“…Most studies are based on the global urban environment, while finer urban areas are rarely involved. More importantly, few efforts have associated image recognition with urban change [10,36]. Nevertheless, urban dynamics play an important role in understanding cities, especially for the perceived urban spaces that reflect human interactions with the built environment.…”

Didactic use of GIS and Street View for Tourism Degree students: understanding commercial gentrification in large urban destinations

“…Regarding the research methodologies, conventional techniques include census data treatment (sometimes in GIS), fieldwork, surveys and in-depth interviews. However, with great potential is the Street View tool embedded in Google Maps which has been considered only recently and exceptionally as an important data source in tourism research (Ilic, Sawada, & Zarzelli, 2019).…”