Physical environment features that predict outdoor active play can be measured using Google Street View images
Abstract 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...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-09-01
|
| Series: | International Journal of Health Geographics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12942-023-00346-3 |
| _version_ | 1797451600861593600 |
|---|---|
| author | Randy Boyes William Pickett Ian Janssen David Swanlund Nadine Schuurman Louise Masse Christina Han Mariana Brussoni |
| author_facet | Randy Boyes William Pickett Ian Janssen David Swanlund Nadine Schuurman Louise Masse Christina Han Mariana Brussoni |
| author_sort | Randy Boyes |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-09T14:57:00Z |
| format | Article |
| id | doaj.art-4daad595d45c46408e2b2cd986644b7a |
| institution | Directory Open Access Journal |
| issn | 1476-072X |
| language | English |
| last_indexed | 2024-03-09T14:57:00Z |
| publishDate | 2023-09-01 |
| publisher | BMC |
| record_format | Article |
| series | International Journal of Health Geographics |
| spelling | doaj.art-4daad595d45c46408e2b2cd986644b7a2023-11-26T14:07:39ZengBMCInternational Journal of Health Geographics1476-072X2023-09-0122111210.1186/s12942-023-00346-3Physical environment features that predict outdoor active play can be measured using Google Street View imagesRandy Boyes0William Pickett1Ian Janssen2David Swanlund3Nadine Schuurman4Louise Masse5Christina Han6Mariana Brussoni7Department of Public Health Sciences, Queen’s UniversityDepartment of Public Health Sciences, Queen’s UniversityDepartment of Public Health Sciences, Queen’s UniversityDepartment of Geography, Simon Fraser UniversityDepartment of Geography, Simon Fraser UniversitySchool of Population and Public Health, University of British Columbia, British Columbia Children’s HospitalDepartment of Pediatrics, School of Population and Public Health, Human Early Learning Partnership, University of British Columbia, British Columbia Children’s HospitalDepartment of Pediatrics, School of Population and Public Health, Human Early Learning Partnership, University of British Columbia, British Columbia Children’s HospitalAbstract 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.https://doi.org/10.1186/s12942-023-00346-3ChildBuilt environmentSocial factorsCitiesExercisePlay |
| spellingShingle | Randy Boyes William Pickett Ian Janssen David Swanlund Nadine Schuurman Louise Masse Christina Han Mariana Brussoni Physical environment features that predict outdoor active play can be measured using Google Street View images International Journal of Health Geographics Child Built environment Social factors Cities Exercise Play |
| title | Physical environment features that predict outdoor active play can be measured using Google Street View images |
| title_full | Physical environment features that predict outdoor active play can be measured using Google Street View images |
| title_fullStr | Physical environment features that predict outdoor active play can be measured using Google Street View images |
| title_full_unstemmed | Physical environment features that predict outdoor active play can be measured using Google Street View images |
| title_short | Physical environment features that predict outdoor active play can be measured using Google Street View images |
| title_sort | physical environment features that predict outdoor active play can be measured using google street view images |
| topic | Child Built environment Social factors Cities Exercise Play |
| url | https://doi.org/10.1186/s12942-023-00346-3 |
| work_keys_str_mv | AT randyboyes physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages AT williampickett physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages AT ianjanssen physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages AT davidswanlund physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages AT nadineschuurman physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages AT louisemasse physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages AT christinahan physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages AT marianabrussoni physicalenvironmentfeaturesthatpredictoutdooractiveplaycanbemeasuredusinggooglestreetviewimages |