Advancements in Real-Time Social Distance Detection: Harnessing AI and Computer Vision for Public Health and Safety
Piyush Vashistha, Ritesh Kumar Singh, Sanjeev Kumar, Mahi Saxena · 2024
This research paper explores the development of real-time social distance detection systems that utilize cutting-edge artificial intelligence and computer vision technologies. These systems are designed to monitor and classify individuals' adherence to social distancing guidelines, especially in scenarios where crowd management is crucial. The paper reviews various approaches to social distance detection, encompassing techniques using thermal cameras, video surveillance, and deep learning. YOLO-NAS establishes a new benchmark in the realm of object detection models, redefining the balance between accuracy and latency. It discusses the implementation of these technologies in practical applications, such as monitoring crowded public spaces or events. Key findings and results from the research highlight the accuracy and effectiveness of these systems in identifying social distancing violations. The study also emphasizes the importance of such technology in promoting public health and safety during disease outbreaks, emphasizing its utility in pandemic management. This research paper contributes valuable insights into the realm of social distance detection, offering a foundation for the development and deployment of real-time systems that can aid in maintaining safe distancing practices, particularly in challenging and high-traffic environments.