Imperial College London
Portrait Picture

ProfessorMajidEzzati

Faculty of Medicine, School of Public Health

Chair in Global Environmental Health
 
 
 
//

Contact

 

majid.ezzati Website

 
 
//

Location

 

Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Nathvani:2022:10.1038/s41598-022-24474-1,
author = {Nathvani, R and Clark, S and Muller, E and Alli, A and Bennett, J and Nimo, J and Moses, J and Baah, S and Metzler, A and Brauer, M and Suel, E and Hughes, A and Rashid, T and Gemmel, E and Moulds, S and Baumgartner, J and Toledano, M and Agyemang, E and Owusu, G and Agyei-Mensah, S and Arku, R and Ezzati, M},
doi = {10.1038/s41598-022-24474-1},
journal = {Scientific Reports},
title = {Characterisation of urban environment and activity across space and time using street images and deep learning in Accra},
url = {http://dx.doi.org/10.1038/s41598-022-24474-1},
volume = {12},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The urban environment influences human health, safety and wellbeing. Cities in Africa are growing faster than other regions but have limited data to guide urban planning and policies. Our aim was to use smart sensing and analytics to characterise the spatial patterns and temporal dynamics of features of the urban environment relevant for health, liveability, safety and sustainability. 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 augmentation to retrain a convolutional neural network to detect them in the remaining images. We identified 23.5 million instances of these objects including 9.66 million instances of persons (41% of all objects), followed by cars (4.19 million, 18%), umbrellas (3.00 million, 13%), and informally operated minibuses known as tro tros (2.94 million, 13%). People, large vehicles and market-related objects were most common in the commercial core and densely populated informal neighbourhoods, while refuse and animals were most observed in the peripheries. The daily variability of objects was smallest in densely populated settlements and largest in the commercial centre. Our novel data and methodology shows that smart sensing and analytics can inform planning and policy decisions for making cities more liveable, equitable, sustainable and healthy.
AU  - Nathvani,R
AU  - Clark,S
AU  - Muller,E
AU  - Alli,A
AU  - Bennett,J
AU  - Nimo,J
AU  - Moses,J
AU  - Baah,S
AU  - Metzler,A
AU  - Brauer,M
AU  - Suel,E
AU  - Hughes,A
AU  - Rashid,T
AU  - Gemmel,E
AU  - Moulds,S
AU  - Baumgartner,J
AU  - Toledano,M
AU  - Agyemang,E
AU  - Owusu,G
AU  - Agyei-Mensah,S
AU  - Arku,R
AU  - Ezzati,M
DO  - 10.1038/s41598-022-24474-1
PY  - 2022///
SN  - 2045-2322
TI  - Characterisation of urban environment and activity across space and time using street images and deep learning in Accra
T2  - Scientific Reports
UR  - http://dx.doi.org/10.1038/s41598-022-24474-1
UR  - http://hdl.handle.net/10044/1/101836
VL  - 12
ER  -
Download