Crowd Management Surveillance using Artificial Intelligence and Deep Learning

Authors: Vaibhav Bilade, Chetan Fulaware, Ankita Gaikwad, P.Y. Sanvatsarkar

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: In today’s rapidly evolving technological landscape, the integration of artificial intelligence (AI) in video surveillance systems has emerged as a paramount solution to address diverse safety and security challenges. This paper presents an AI-powered video surveillance system that leverages advanced computer vision techniques to enhance situational awareness in real-time video streams, both from recorded video input and live web cameras. The system incorporates the following key features:

1. Fall Detection: The system utilizes AI algorithms to detect and promptly respond to incidents of individuals falling within the surveillance area. By identifying such events, the system ensures rapid assistance, especially for vulnerable populations, thereby mitigating potential harm and reducing emergency response time.

2. Overcrowd Detection: Overcrowding in public spaces is a common safety concern. Our system employs AI to analyze video feeds and identify instances of overcrowding. This enables authorities to take proactive measures to manage crowd density, maintain public safety, and prevent potential emergencies.

3. Fire and Weapon Detection: Early detection of fires and weapons is crucial for public safety and security. The AI-powered system is designed to identify instances of fires and the presence of weapons within the surveillance area. This capability allows for rapid response to fire emergencies and potential threats, ultimately safeguarding lives and property.

The system supports real-time video analysis from both recorded video input and live web cameras, making it versatile and adaptable for a wide range of applications.

Keywords:

Paper Id: 230615

Published On: 2024-04-27

Published In: Volume 12, Issue 2, March-April 2024

Cite This: Crowd Management Surveillance using Artificial Intelligence and Deep Learning - Vaibhav Bilade, Chetan Fulaware, Ankita Gaikwad, P.Y. Sanvatsarkar - IJIRMPS Volume 12, Issue 2, March-April 2024.

Share this