Estimating Interpersonal Distance and Crowd Density with a Single-Edge Camera

Abstract

For public safety and physical security, currently more than a billion closed-circuit television (CCTV) cameras are in use around the world. Proliferation of artificial intelligence (AI) and machine/deep learning (M/DL) technologies have gained significant applications including crowd surveillance. The state-of-the-art distance and area estimation algorithms either need multiple cameras or a reference object as a ground truth. It is an open question to obtain an estimation using a single camera without a scale reference. In this paper, we propose a novel solution called E-SEC, which estimates interpersonal distance between a pair of dynamic human objects, area occupied by a dynamic crowd, and density using a single edge camera. The E-SEC framework comprises edge CCTV cameras responsible for capturing a crowd on video frames leveraging a customized YOLOv3 model for human detection. E-SEC contributes an interpersonal distance estimation algorithm vital for monitoring the social distancing of a crowd, and an area estimation algorithm for dynamically determining an area occupied by a crowd with changing size and position. A unified output module generates the crowd size, interpersonal distances, social distancing violations, area, and density per every frame. Experimental results validate the accuracy and efficiency of E-SEC with a range of different video datasets.

Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey

“…To that end, as explained in Yang, Sun, et al (2021) , a simple algorithm that helps calculate the Euclidean distance matrix for all detected pedestrians can easily be implemented to detect potential SD violation pairs in each video scene. Moreover, as another example, in Fitwi, Chen, Sun, and Harrod (2021) , an interpersonal distance measurement algorithm based on triangle similarity is introduced to monitor the SD of crowds in real-time. This work relies on edge CCTV cameras, which capture crowds on video frames and leverage a YOLOv3 model to detect pedestrians.…”

“…For instance, the solution developed in Rezaei and Azarmi (2020) performs real-time monitoring using either a 10th generation multi-core/multi-thread CPU platform (or higher) or a basic GPU platform. Moving forward, in Fitwi et al (2021) , a powerful Predator Triton 700-A laptop equipped with a GPU card has been used to process more than 20 FPS. Moving on, the YOLOv4-based VSDM system presented in Rahim et al (2021) has been implemented on a Tesla T4 GPU with 16 GB memory.…”

Vision-Based Self-Adaptive Gripping in a Trimodal Robotic Sorting End-Effector

“…Finally, by using the pixels_per_metric [17] method the actual size of the object will be determined. ) will be determined in x and y coordinates in the next step.…”

Security Measures: Effectiveness of the Installation of CCTV Cameras in Relation to Crime Prevention as Perceived by the Community

“…That is why CCTV camera serves many functions and is widely used in both public and private places. CCTV cameras are video cameras used for the purpose of security and observing a certain area (Fitwi et al, 2021).…”