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

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.

New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection

“…We need to design a more specific system to solve this problem. Several techniques and approaches exist, some try to estimate the number of people directly [2,3] and others try to go through an intermediate step by calculating a density of people in the image [4,5]. The latter allows retrieval of more information and a better interpretation of images.…”

Crowd Control Strategies in Casinos in Lagos State, Nigeria

“…Angitso & Eze, (2019)"Crowd" refers to a large gathering of people who may be united by a shared interest or feelings, as at sporting events and political demonstrations. According to Gong et al, (2021)The layout of a venue, the design of circulation routes, and the placement and design of facilities, among other factors, can significantly impact crowd behavior. Inter-group perspective Observing and understanding how the in-group is a group that shares certain traits and functions is crucial.…”

Identification and Classification of Crowd Activities

“…The second most difficult challenge is multiple object tracking, which localizes detected persons along with the video [12]. Thirdly, the computation of calculating the total number of individuals is considered the third challenging problem [13]. Challenges appear due to occlusions, constant displacement of the person, varied viewpoints and behavior, varying levels of illumination, and the allocation of pixels per person decreases in high density.…”