DETECTING SOCIAL DISTANCING USING DEEP LEARNING AND ARTIFICIAL INTELLIGENCE

Computer Science and Engineering

In recent years, the world has witnessed unprecedented challenges brought about by the outbreak of infectious diseases, such as COVID-19, that require rapidand effective responses to ensure public health and safety. Social distancing has emerged as a crucial measure to mitigate the spread of contagious diseases in crowded settings. However, monitoring and enforcing social distancing in crowdedspaces can be a complex and resource-intensive task. This project presents a novel approach to address this challenge by harnessing the power of big data analytics, deep learning, and artificial intelligence (AI). We propose a system for crowd surveillance that leverages advanced computer vision techniques to monitor socialdistancing compliance in real-time. The key components of oursystem include datacollection, pre- processing, deep learning-based object detection, and intelligent decision-making. The data collection process involves the deployment of high-resolution cameras and sensors in public areas and other crowded spaces. These devices continuously capture video and sensor data, creating a massive influx of information. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are used to analyze visual data, identify individuals, and track their movements. Our big data-enabled crowd surveillance system provides real-time insights into social distancing compliance, allowing for rapid intervention when violations occur. By leveraging the power of big data and AI, our system can enhance public health and safety efforts in crowded environments,contributing to the containment of infectious diseases. This project outlines a cutting-edge approach to crowd surveillance for social distancing using big data analytics, deep learning, and artificial intelligence.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.