Journal of safety research · 2023
Computer vision-based helmet use registration for e-scooter riders - The impact of the mandatory helmet law in Copenhagen.
Наблюдательное исследованиеСтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Siebert Felix Wilhelm, Riis Christoffer, Janstrup Kira Hyldekær, Lin Hanhe, Hüttel Frederik Boe
Аннотация
PROBLEM: E-scooters are a new form of mobility used more frequently in urban environments worldwide. As there is evidence of an increased risk of head injuries, helmets are recommended and (less frequently) legislated. Denmark has enacted mandatory e-scooter helmet use legislation from January 1, 2022. So far, it is unclear how this newly implemented law influenced helmet use of e-scooter riders in Denmark immediately after its implementation.
METHOD: In this observational study, we register and compare e-scooter helmet use before the mandatory helmet use legislation (December 2021) and after (February 2022). As observational survey data collection in the field can be highly time-consuming, we conducted a video-based observation survey. We trained and applied a computer vision algorithm to automatically register e-scooter helmet use in the video data.
RESULTS: The trained algorithm produces accurate helmet use data, which does not differ significantly from human-registered helmet use. In applying the algorithm to video data collected in December 2021 and February 2022, we register an overall e-scooter helmet use of 4.4% in n = 1054 riders. Splitting the observation between the time before and after the implementation of the helmet use law reveals a significant increase in helmet use from 1.80% to 5.56%.
DISCUSSION: In this study, we successfully train and apply an object detection algorithm to register accurate helmet use data in videos collected in Copenhagen, Denmark. Using this algorithm, we find a significant impact of a new mandatory e-scooter helmet use law on e-scooter riders' helmet use behavior. Limitations of the study as well as future research needs, are discussed.
PRACTICAL APPLICATIONS: Computer vision algorithms can be used for accurate e-scooter helmet assessments. Implementing a mandatory helmet use law can increase helmet use of e-scooters at specific observation sites.
METHOD: In this observational study, we register and compare e-scooter helmet use before the mandatory helmet use legislation (December 2021) and after (February 2022). As observational survey data collection in the field can be highly time-consuming, we conducted a video-based observation survey. We trained and applied a computer vision algorithm to automatically register e-scooter helmet use in the video data.
RESULTS: The trained algorithm produces accurate helmet use data, which does not differ significantly from human-registered helmet use. In applying the algorithm to video data collected in December 2021 and February 2022, we register an overall e-scooter helmet use of 4.4% in n = 1054 riders. Splitting the observation between the time before and after the implementation of the helmet use law reveals a significant increase in helmet use from 1.80% to 5.56%.
DISCUSSION: In this study, we successfully train and apply an object detection algorithm to register accurate helmet use data in videos collected in Copenhagen, Denmark. Using this algorithm, we find a significant impact of a new mandatory e-scooter helmet use law on e-scooter riders' helmet use behavior. Limitations of the study as well as future research needs, are discussed.
PRACTICAL APPLICATIONS: Computer vision algorithms can be used for accurate e-scooter helmet assessments. Implementing a mandatory helmet use law can increase helmet use of e-scooters at specific observation sites.