Abstract
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.
Highlights
City events, such as sports matches, thematic carnivals and national annual festivals, are carried out in urban areas, and may attract a large number of people during a short time period
We 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
The image characteristics consist of requirements from crowd management such as indoor/outdoor and urban environment shown in each image, and characteristics of images posted from social media in terms of, e.g. image type and distribution of crowds, that may affect the performance of crowd counting methods
Summary
City events, such as sports matches, thematic carnivals and national annual festivals, are carried out in urban areas, and may attract a large number of people during a short time period. A higher level-of-service of the event area indicates lower density of people in that area, which is safer than the lower level-of-service that refers to high density of people. Using such information together with a set of other qualitative and quantitative interpretation of the crowd, such as sentiment (Gong et al 2019) and composition (Gong et al 2018a), stakeholders apply predefined measures to manage the crowd. To estimate the level-of-service in a popular attraction such as the Dam Square in the Amsterdam during the King’s Day for crowd management, we can calculate the density of crowd in that area. The number of people in the crowd is a valuable input for estimating the level-of-service in event area, and further for crowd management
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
