Estimating Vehicle and Pedestrian Activity from Town and City Traffic Cameras

Abstract

Traffic cameras are a widely available source of open data that offer tremendous value to public authorities by providing real-time statistics to understand and monitor the activity levels of local populations and their responses to policy interventions such as those seen during the COrona VIrus Disease 2019 (COVID-19) pandemic. This paper presents an end-to-end solution based on the Google Cloud Platform with scalable processing capability to deal with large volumes of traffic camera data across the UK in a cost-efficient manner. It describes a deep learning pipeline to detect pedestrians and vehicles and to generate mobility statistics from these. It includes novel methods for data cleaning and post-processing using a Structure SImilarity Measure (SSIM)-based static mask that improves reliability and accuracy in classifying people and vehicles from traffic camera images. The solution resulted in statistics describing trends in the ‘busyness’ of various towns and cities in the UK. We validated time series against Automatic Number Plate Recognition (ANPR) cameras across North East England, showing a close correlation between our statistical output and the ANPR source. Trends were also favorably compared against traffic flow statistics from the UK’s Department of Transport. The results of this work have been adopted as an experimental faster indicator of the impact of COVID-19 on the UK economy and society by the Office for National Statistics (ONS).

A systematic review of observational methods used to quantify personal protective behaviours among members of the public during the COVID-19 pandemic, and the concordance between observational and self-report measures in infectious disease health protection

“…Improving uptake of health protective behaviours is an important public health challenge, not only for COVID-19, but for infectious disease prevention more widely. Face coverings, hand hygiene and maintaining physical distance have all been identified as effective infection control strategies that have relatively few downsides in comparison to more far-reaching interventions such as society-wide ‘lockdowns’ [ 11 ]. Identifying ways to achieve good adherence to such measures requires that we are first able to measure adherence accurately.…”

“…In the context of COVID-19, regularly collected measures of behaviour that do not rely on self-report are rare. Notable exceptions include: mobility data based on mobile phone locations [ 10 ]; footfall data in city centres [ 11 ]; and official statistics on vaccine uptake based on electronic records [ 12 ]. Most of these examples relate to where people are located or whether they engage with health services.…”

A systematic review of observational methods used to quantify personal protective behaviours among members of the public during the COVID-19 pandemic, and the concordance between observational and self-report measures in infectious disease health protection

“…Improving uptake of health protective behaviours is an important public health challenge, not only for COVID-19, but for infectious disease prevention more widely. Face coverings, hand hygiene and maintaining physical distance have all been identified as effective infection control strategies that have relatively few downsides in comparison to more far-reaching interventions such as society-wide ‘lockdowns.’ 12 Identifying ways to achieve good adherence to such measures requires that we are first able to measure adherence accurately. Though self-report can be a useful proxy for behaviour, our review suggests that academic research has become overly reliant on it, so much so that although we identified 27, 279 papers which included terms related to COVID-19 and to hand hygiene, face covering or social distancing, just 48 of these papers (<0.2%) actually studied the behaviour in question objectively.…”

“…In the context of COVID-19, regularly collected measures of behaviour that do not rely on self-report are rare. Notable exceptions include: mobility data based on mobile phone locations 11 ; footfall data in city centres 12 ; and official statistics on vaccine uptake based on electronic records 13 . Most of these examples relate to where people are located or whether they engage with health services.…”

Characterization of COVID-19’s Impact on Mobility and Short-Term Prediction of Public Transport Demand in a Mid-Size City in Spain

“…With respect to data-driven studies, we can find specific works on private vehicle and public transport that treat them separately, thus lacking of an integrated view. The former focuses on analyzing the impact of the pandemic and the subsequent restrictions on traffic flows as in [ 26 ] (Rome, Italy), [ 27 ] (Qatar), [ 28 ] (several locations in the UK), and [ 29 ] (Slovakia), and its positive effects on pollution [ 26 , 30 , 31 ], and accidents [ 32 ]. Among the works that study the pandemic’s impact particularly related with public transport using data-driven analyses, let us highlight the following research.…”