Patterns of motorcycle helmet use – A naturalistic observation study in Myanmar

Abstract

Developing countries are subject to increased motorization, particularly in the number of motorcycles. As helmet use is critical to the safety of motorcycle riders, the goal of this study was to identify observable patterns of helmet use, which allow a more accurate assessment of helmet use in developing countries. In a video based observation study, 124,784 motorcycle riders were observed at seven observation sites throughout Myanmar. Recorded videos were coded for helmet use, number of riders on the motorcycle, rider position, gender, and time of day. Generally, motorcycle helmet use in Myanmar was found to be low with only 51.5% percent of riders wearing a helmet. Helmet use was highest for drivers (68.1%) and decreased for every additional passenger. It was lowest for children standing on the floorboard of the motorcycle (11.3%). During the day, helmet use followed a unimodal distribution, with the highest use observed during the late morning and lowest use observed in the early morning and late afternoon. Helmet use varied significantly between observation sites, ranging from 74.8% in Mandalay to 26.9% in Pakokku. In Mandalay, female riders had a higher helmet use than male riders, and helmet use decreased drastically on a national holiday in the city.Helmet use of motorcycle riders in Myanmar follows distinct patterns. Knowledge of these patterns can be used to design more precise helmet use evaluations and guide traffic law policy and police enforcement measures. Video based observation proved to be an efficient tool to collect helmet use data.

Detecting motorcycle helmet use with deep learning

“…7. Helmet use was either reg-istered by a human observer [4], registered through the trained algorithm, or the untrained algorithm. It can be observed that hourly helmet use percentages are relatively similar when comparing human and computer registered rates of the trained algorithm.…”

“…It is important to understand the fundamental difference of the hand-counting method used by Siebert et al [4] and the frame-based algorithmic approach pre- In contrast, the computer vision approach developed in this paper will register motorcycle riders' helmet use in each frame where a motorcycle is detected.…”

“…Since the video data that forms the basis for the training of the machine learning algorithm in this paper has been analyzed in the past to assess motorcycle helmet use, there is a unique opportunity to compare hand-counted helmet use numbers in the video data with the calculated helmet use numbers generated by the algorithm developed in this paper. Siebert et al [4] hand-counted the motorcyclists with and without helmets in the source video data for the first 15 minutes of every hour that a video was recorded. Hence, "hourly" helmet use percentages for every individual observation site in the data set are available.…”

“…However, 40% of countries in the world do not have an estimate of this crucial road safety metric [5]. And even if data is available, helmet use observations are frequently limited in sample size and regional scope [6,7], draw from data of relatively short time frames [8,9], or are only singularly collected in the scope of academic research [4,10]. The main reason for this lack of comprehensive continuous data lies in the prevailing way of helmet use data collection, which utilizes direct observation of motorcycle helmet use in traffic by human observers.…”

Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning

“…In particular the lack of rider differentiation is a crucial element for the application of automated helmet use detection in the field. Researchers repeatedly find evidence of an influence of rider position and rider number on helmet use on individual motorcycles [12]- [15]. Hence, the differentiation of rider helmet use for drivers and passengers is a crucial metric, that should not be omitted in automated detection approaches.…”