A Deep-Learning Method for the Prediction of Socio- Economic Indicators from Street-View Imagery Using a Case Study from Brazil
Following a study in the streets of London by Suel et al.* (2019) we used Google Street View (GSV) images as our source of remote observations to predict socioeconomic indicators using street-view imagery, through a case study conducted in a region of Brazil, the Vale do Ribeira, one of the poorest semi-rural regions in Brazil. We found that the method has the potential to predict socioeconomic indicators across a large area with social challenges, and the CNN network model we developed is general enough to be used even when the imagery dataset is from semi-rural areas, remembering that the resource is not systematically collected or published. To aid in the replicability of this study, therefore, we have published our source code as follows: https://github.com/PARSECworld/streetsValeRibeira and released at https://doi.org/10.5281/zenodo.4898335.
*Suel et al. (2019) doi: 10.1038/s41598-019-42036-w
citation: Machicao, J., Specht, A., Vellenich, D., Meneguzzi, L., David, R., Stall, S., Ferraz, K., Mabile, L., O’Brien, M.,Corrêa, P., 2022. Data Science Journal 21, 6. https://doi.org/10.5334/dsj-2022-006