A deep learning approach to identify unhealthy advertisements in street view images
This addresses the need for efficient data collection to evaluate policy restrictions on advertisements that may exacerbate health inequalities for vulnerable populations, though it is incremental as it applies existing deep learning methods to a new domain.
The researchers tackled the problem of manually identifying unhealthy advertisements in street-level images by developing a deep learning workflow to automatically extract and classify them, using a new dataset of 25,349 images and finding that a larger proportion of food ads are in deprived areas.
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 encouraging 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 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) (e.g., cars and broadband). 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.