Monitoring the Number of Pedestrians in an Area: The Applicability of Counting Systems for Density State Estimation

Abstract

Crowd monitoring systems are more and more used to support crowd management organizations. Currently, counting systems are often used to provide quantitative insights into the pedestrian traffic state, since they are fairly easy to install and the accuracy is reasonably good under normal conditions. However, there are no sensor systems that are 100% accurate. Detection errors might have severe consequences for the density state estimation at large squares. The consequences of these errors for pedestrian state estimation have not yet been determined. This paper studies the impact of one specific type of detection error on the functionality of counting camera systems for density state estimation, namely, a randomly occurring "false negative" detection error. The impact is determined via two tracks, a theoretical track and a simulation track. The latter track studies the distribution of the cumulative number of pedestrians after 24 hours for three stylized cases by means of Monte Carlo simulations. This paper finds that counting camera systems, which have a detection error that is not correlated with the flow rate, provide a reasonably good estimation of the density within an area. At the same time, if the detection error is correlated with the flow rate, counting camera systems should only be used in the situation where symmetric demand patterns are expected.

An experimental contingent valuation of users’ attitudes towards a Crowd Management System

“…A WTP value (HK$4.51) was obtained from the pooled model using all 430 valid samples. As the first pilot CMS in Hong Kong, unfamiliarity with it may contribute to the deviation of the estimation between the on-the-spot and off-site models (Duives et al, 2018). Whilst the 95% confidence interval for the WTP of the on-the-spot survey (HK$2.98 to HK$3.77) overlaps with that of the off-site survey (HK$3.24 to HK$5.41), and the pooled samples yield a 95% confidence interval as HK$3.69 to HK$5.44 (see Table 5), it is a reasonable compromise to adopt HK$3.69, which is almost the midpoint of the overlapped region, as the estimated WTP for the CMS, with preferred conservatism in the benefit valuation.…”

Pedestrian age estimation based on deep learning

“…The report recommended the need to improve the roads infrastructure, which represents the main cause of the fatal injury in road traffic collisions [1]. Pedestrian monitoring systems provide quantitative insights into the pedestrian traffic state, although they are easy to install and good under normal conditions, but they are not 100% accurate [2]. This work focuses on age estimation for specific age groups, since elderly people fall during across the street is among the most damaging event and the most common occurrence, beside the children between those two phases, ages 4 through 10.…”