Characterisation of urban environment and activity across space and time using street images and deep learning in Accra.
Nathvani R, Clark SN, Muller E, Alli AS, Bennett JE, Nimo J, Moses JB, Baah S, Metzler AB, Brauer M, Suel E, Hughes AF, Rashid T, Gemmell E, Moulds S, Baumgartner J, Toledano M, Agyemang E, Owusu G, Agyei-Mensah S, Arku RE, Ezzati M.
Nathvani R, et al.
Sci Rep. 2022 Nov 28;12(1):20470. doi: 10.1038/s41598-022-24474-1.
Sci Rep. 2022.
PMID: 36443345
Free PMC article.
We collected a novel dataset of 2.1 million time-lapsed day and night images at 145 representative locations throughout the Metropolis of Accra, Ghana. We manually labelled a subset of 1,250 images for 20 contextually relevant objects and used transfer learning with data a …
We collected a novel dataset of 2.1 million time-lapsed day and night images at 145 representative locations throughout the Metropolis of Ac …