Physical environment features that predict outdoor active play can be measured using Google Street View images.
Built environment
Child
Cities
Exercise
Play
Social factors
Journal
International journal of health geographics
ISSN: 1476-072X
Titre abrégé: Int J Health Geogr
Pays: England
ID NLM: 101152198
Informations de publication
Date de publication:
28 09 2023
28 09 2023
Historique:
received:
18
04
2023
accepted:
14
09
2023
medline:
29
9
2023
pubmed:
28
9
2023
entrez:
27
9
2023
Statut:
epublish
Résumé
Childrens' outdoor active play is an important part of their development. Play behaviour can be predicted by a variety of physical and social environmental features. Some of these features are difficult to measure with traditional data sources. This study investigated the viability of a machine learning method using Google Street View images for measurement of these environmental features. Models to measure natural features, pedestrian traffic, vehicle traffic, bicycle traffic, traffic signals, and sidewalks were developed in one city and tested in another. The models performed well for features that are time invariant, but poorly for features that change over time, especially when tested outside of the context where they were initially trained. This method provides a potential automated data source for the development of prediction models for a variety of physical and social environment features using publicly accessible street view images.
Sections du résumé
BACKGROUND
Childrens' outdoor active play is an important part of their development. Play behaviour can be predicted by a variety of physical and social environmental features. Some of these features are difficult to measure with traditional data sources.
METHODS
This study investigated the viability of a machine learning method using Google Street View images for measurement of these environmental features. Models to measure natural features, pedestrian traffic, vehicle traffic, bicycle traffic, traffic signals, and sidewalks were developed in one city and tested in another.
RESULTS
The models performed well for features that are time invariant, but poorly for features that change over time, especially when tested outside of the context where they were initially trained.
CONCLUSION
This method provides a potential automated data source for the development of prediction models for a variety of physical and social environment features using publicly accessible street view images.
Identifiants
pubmed: 37759295
doi: 10.1186/s12942-023-00346-3
pii: 10.1186/s12942-023-00346-3
pmc: PMC10536757
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
26Subventions
Organisme : CIHR
ID : MOP-142262
Pays : Canada
Informations de copyright
© 2023. BioMed Central Ltd., part of Springer Nature.
Références
J Public Health (Oxf). 2018 Mar 1;40(1):8-15
pubmed: 28039198
BMC Public Health. 2016 Aug 19;16(1):829
pubmed: 27538781
Prev Med. 2015 Jul;76:31-6
pubmed: 25869220
Asia Pac J Public Health. 2016 Jul;28(5 Suppl):21S-34S
pubmed: 27026634
Health Place. 2018 Jul;52:240-246
pubmed: 30015181
Int J Behav Nutr Phys Act. 2015 Jan 24;12:5
pubmed: 25616690
Health Place. 2018 Sep;53:237-257
pubmed: 30196042
Qual Life Res. 2019 Jul;28(7):1695-1703
pubmed: 30746588
Obes Rev. 2021 Feb;22 Suppl 1:e12943
pubmed: 31507068
Curr Obes Rep. 2015 Dec;4(4):477-83
pubmed: 26399254
IEEE Trans Pattern Anal Mach Intell. 2018 Apr;40(4):834-848
pubmed: 28463186
Am J Public Health. 2003 Sep;93(9):1390-4
pubmed: 12948949