A deep learning approach to identify unhealthy advertisements in street view images
Abstract While outdoor advertisements are common features within towns and cities, they may reinforce social inequalities in health. Vulnerable populations in deprived areas may have greater exposure to fast food, gambling and alcohol advertisements, which may encourage their consumption. Understand...
Guardado en:
Autores principales: | , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/d117b04462664ea4af4b0794b6d30ede |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:d117b04462664ea4af4b0794b6d30ede |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:d117b04462664ea4af4b0794b6d30ede2021-12-02T15:54:01ZA deep learning approach to identify unhealthy advertisements in street view images10.1038/s41598-021-84572-42045-2322https://doaj.org/article/d117b04462664ea4af4b0794b6d30ede2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84572-4https://doaj.org/toc/2045-2322Abstract While outdoor advertisements are common features within towns and cities, they may reinforce social inequalities in health. Vulnerable populations in deprived areas may have greater exposure to fast food, gambling and alcohol advertisements, which may encourage their consumption. Understanding who is exposed and evaluating potential policy restrictions requires a substantial manual data collection effort. To address this problem we develop a deep learning workflow to automatically extract and classify unhealthy advertisements from street-level images. We introduce the Liverpool $${360}^{\circ }$$ 360 ∘ Street View (LIV360SV) dataset for evaluating our workflow. The dataset contains 25,349, 360 degree, street-level images collected via cycling with a GoPro Fusion camera, recorded Jan 14th–18th 2020. 10,106 advertisements were identified and classified as food (1335), alcohol (217), gambling (149) and other (8405). We find evidence of social inequalities with a larger proportion of food advertisements located within deprived areas and those frequented by students. Our project presents a novel implementation for the incidental classification of street view images for identifying unhealthy advertisements, providing a means through which to identify areas that can benefit from tougher advertisement restriction policies for tackling social inequalities.Gregory PalmerMark GreenEmma BoylandYales Stefano Rios VasconcelosRahul SavaniAlex SingletonNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Gregory Palmer Mark Green Emma Boyland Yales Stefano Rios Vasconcelos Rahul Savani Alex Singleton A deep learning approach to identify unhealthy advertisements in street view images |
description |
Abstract While outdoor advertisements are common features within towns and cities, they may reinforce social inequalities in health. Vulnerable populations in deprived areas may have greater exposure to fast food, gambling and alcohol advertisements, which may encourage their consumption. Understanding who is exposed and evaluating potential policy restrictions requires a substantial manual data collection effort. To address this problem we develop a deep learning workflow to automatically extract and classify unhealthy advertisements from street-level images. We introduce the Liverpool $${360}^{\circ }$$ 360 ∘ Street View (LIV360SV) dataset for evaluating our workflow. The dataset contains 25,349, 360 degree, street-level images collected via cycling with a GoPro Fusion camera, recorded Jan 14th–18th 2020. 10,106 advertisements were identified and classified as food (1335), alcohol (217), gambling (149) and other (8405). We find evidence of social inequalities with a larger proportion of food advertisements located within deprived areas and those frequented by students. Our project presents a novel implementation for the incidental classification of street view images for identifying unhealthy advertisements, providing a means through which to identify areas that can benefit from tougher advertisement restriction policies for tackling social inequalities. |
format |
article |
author |
Gregory Palmer Mark Green Emma Boyland Yales Stefano Rios Vasconcelos Rahul Savani Alex Singleton |
author_facet |
Gregory Palmer Mark Green Emma Boyland Yales Stefano Rios Vasconcelos Rahul Savani Alex Singleton |
author_sort |
Gregory Palmer |
title |
A deep learning approach to identify unhealthy advertisements in street view images |
title_short |
A deep learning approach to identify unhealthy advertisements in street view images |
title_full |
A deep learning approach to identify unhealthy advertisements in street view images |
title_fullStr |
A deep learning approach to identify unhealthy advertisements in street view images |
title_full_unstemmed |
A deep learning approach to identify unhealthy advertisements in street view images |
title_sort |
deep learning approach to identify unhealthy advertisements in street view images |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/d117b04462664ea4af4b0794b6d30ede |
work_keys_str_mv |
AT gregorypalmer adeeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT markgreen adeeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT emmaboyland adeeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT yalesstefanoriosvasconcelos adeeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT rahulsavani adeeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT alexsingleton adeeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT gregorypalmer deeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT markgreen deeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT emmaboyland deeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT yalesstefanoriosvasconcelos deeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT rahulsavani deeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages AT alexsingleton deeplearningapproachtoidentifyunhealthyadvertisementsinstreetviewimages |
_version_ |
1718385477508136960 |