Using Social Media for Attendees Density Estimation in City-Scale Events

Gong, Vincent X.; Yang, Jie; Daamen, Winnie; Bozzon, Alessandro; Hoogendoorn, Serge P.; Houben, Geert‐Jan

doi:10.1109/access.2018.2845339

Cited by 16 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the event, the real-time social media images collected from this event can be used to estimate the current crowd size in the monitoring area. The current crowd size can be used for calculating properties for a crowded urban area, such as the level-of-service (Fruin 1971;Marana et al 1998), crowd density (Gong et al 2018b;Blanke et al 2014;Botta et al 2015;Quercia et al 2015), which can be further used for assessing potential risks (Helbing et al 2005).…”

Section: Discussionmentioning

confidence: 99%

Counting people in the crowd using social media images for crowd management in city events

et al. 2021

Self Cite

View full text Add to dashboard Cite

City events are getting popular and are attracting a large number of people. This increase needs for methods and tools to provide stakeholders with crowd size information for crowd management purposes. Previous works proposed a large number of methods to count the crowd using different data in various contexts, but no methods proposed using social media images in city events and no datasets exist to evaluate the effectiveness of these methods. In this study we investigate how social media images can be used to estimate the crowd size in city events. We construct a social media dataset, compare the effectiveness of face recognition, object recognition, and cascaded methods for crowd size estimation, and investigate the impact of image characteristics on the performance of selected methods. Results show that object recognition based methods, reach the highest accuracy in estimating the crowd size using social media images in city events. We also found that face recognition and object recognition methods are more suitable to estimate the crowd size for social media images which are taken in parallel view, with selfies covering people in full face and in which the persons in the background have the same distance to the camera. However, cascaded methods are more suitable for images taken from top view with gatherings distributed in gradient. The created social media dataset is essential for selecting image characteristics and evaluating the accuracy of people counting methods in an urban event context.

show abstract

Section: Discussionmentioning

confidence: 99%

Counting people in the crowd using social media images for crowd management in city events

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The last data type features social media crawlers, which analyze (geo-posted) messages from popular social media platforms, such as Twitter and Instagram. Social media crawling has been used to study mobility patterns [29], traffic anomalies [30] and the number of people in a restricted area [3,4,31], moreover, mapped demographic information, human movement patterns, and the popularity of Points of Interest (POIs). Social media are most often used to determine aggregate statistics of crowds.…”

Section: Techniques To Monitor Crowd Movement Behaviormentioning

confidence: 99%

“…[2] determined activity patterns and destinations of staff and students on a university campus. Other researchers explored to what extent social media crawlers can be used as a tool to monitor activity schedules and movement behavior of crowds [3,4].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Crowd Monitoring System Functionality through Data Fusion: Estimating Flow Rate from Wi-Fi Traces and Automated Counting System Data

Duives

Oijen

Hoogendoorn

2020

Sensors

View full text Add to dashboard Cite

Crowd monitoring systems (CMSs) provide a state-of-the-art solution to manage crowds objectively. Most crowd monitoring systems feature one type of sensor, which severely limits the insights one can simultaneously gather regarding the crowd’s traffic state. Incorporating multiple functionally complementary sensor types is expensive. CMSs are needed that exploit data fusion opportunities to limit the number of (more expensive) sensors. This research estimates a data fusion algorithm to enhance the functionality of a CMS featuring Wi-Fi sensors by means of a small number of automated counting systems. Here, the goal is to estimate the pedestrian flow rate accurately based on real-time Wi-Fi traces at one sensor location, and historic flow rate and Wi-Fi trace information gathered at other sensor locations. Several data fusion models are estimated, amongst others, linear regression, shallow and recurrent neural networks, and Auto Regressive Moving Average (ARMAX) models. The data from the CMS of a large four-day music event was used to calibrate and validate the models. This study establishes that the RNN model best predicts the flow rate for this particular purpose. In addition, this research shows that model structures that incorporate information regarding the average current state of the area and the temporal variation in the Wi-Fi/count ratio perform best.

show abstract

“…Time is crucial in evacuation situations in case of emergency, while the people's behavior is rather unpredictable and depends of a series of factors such as: age [1], [2], emotions [1], [3]- [6], social background [7], density [8]- [10], environment conditions and localization [11], [12], the presence or absence of guidance or authority figures [1], [13]- [18], geographic features [19], the degree of familiarity with the environment [20], etc.…”

Section: Introductionmentioning

confidence: 99%

Establishing the Proper Seating Arrangement in Elevated Lecture Halls for a Faster Evacuation Process

et al. 2019

View full text Add to dashboard Cite

As time is crucial in the human evacuation process during an emergency situation, several aspects related to how the humans involved in such a process act have been studied over the time, underlying that the humans' behavior is rather unpredictable and depends on social background, emotions, the degree of familiarity with the environment, age, gender, and so on. On the other hand, it has been determined that the characteristics of the environment are important in such situations as they may facilitate a shorter evacuation time. It has been shown that exits characteristics, such as width or their number, have a positive direct impact on the evacuation time. In this context, this paper aims to analyze another environmental aspect, namely, the seat arrangement, and to determine how the seats should be placed in order to reduce the evacuation time for a given configuration of the doors. On this purpose, an elevated lecture hall with two exits has been chosen, as it represents one of the most populated places within the public buildings, characterized not only by a high population density but also by a limited capacity to escape. A case study has been conducted using 97 human subjects and an agent-based model has been created considering their individual characteristics. The model has been simulated on eight different seat arrangements for 15 different positions on the two exitdoors. As a result, the proper seating arrangement for each of the 15 exit-door positions has been presented along with the study's limitations.

show abstract

Using Social Media for Attendees Density Estimation in City-Scale Events

Cited by 16 publications

References 23 publications

Counting people in the crowd using social media images for crowd management in city events

Counting people in the crowd using social media images for crowd management in city events

Enhancing Crowd Monitoring System Functionality through Data Fusion: Estimating Flow Rate from Wi-Fi Traces and Automated Counting System Data

Establishing the Proper Seating Arrangement in Elevated Lecture Halls for a Faster Evacuation Process

Contact Info

Product

Resources

About