What is Social Distancing Monitoring?
Monitoring COVID-19 social distancing with person detection and tracking via deep learning models helps to enforce social distancing as a key strategy to combat the spread of the coronavirus. Deep Neural Networks can be used for automated people detection in the crowd in outdoor and indoor environments using common CCTV cameras.
Social distancing is a recommended solution by the World Health Organization (WHO) to minimize the spread of the coronavirus in public and crowded places. Numerous governments and health authorities have set a 2m physical distancing as a mandatory safety measure in schools, shopping centers, hospitals, and other public places.
Key Features of Social Distancing Recognition
A masked face detection model based on Computer Vision is non-invasive, scalable, and comparably easy to implement since the video feed of any camera can be used.
- Automated multi-person detection and tracking in real-time, using surveillance cameras.
- Analyzing the people’s moving trajectories and rate of social distancing violations.
- Provide a risk assessment scheme for adherence to social distancing guidelines. Track and monitor changes over time.
- Identification of high-risk zones with the greatest danger of possible virus spread.
Value of Automated Social Distancing Detection
AI vision systems use Deep neural networks to provide a scalable approach to automatically analyze social distancing measures in the crowd in indoor and outdoor environments.
- Automation of social distancing monitoring with surveillance cameras, ensuring higher consistency and accuracy compared to human inspection.
- Increase the safety of people, workforces, and customers through highly scalable enforcement of social distancing across multiple locations.
- Save costs of manual inspections while being able to comply with governmental guidelines.
- Identify hot spots and bottlenecks to redesign the layout of public spaces or take precautionary actions to mitigate risks.