AI-Based Real-Time Crowd Detection and Alert System Using YOLOv8

Author(s)	Mr. Krishna Saxena, Mr. Rishi Singh Tomar, Ms. Aarushi Singh, Ms. Shina Sharma, Prof. Vivek Kumar Misra
Country	India
Abstract	Keeping people safe in crowded places like railway stations, transport hubs, and large public events is more challenging than ever. Traditional surveillance systems rely heavily on human operators, who can only watch so many screens at once and often react too slowly when something goes wrong. This paper introduces an AI-powered system that monitors crowds in real time using YOLOv8, a state-of-the-art deep learning model, to take the pressure off human operators and respond to threats the moment they emerge. The system works locally on-device, meaning it doesn't depend on a constant internet connection to function. It can detect individuals in a crowd, gauge how dense a crowd is getting, flag potential safety violations, and fire off automated alerts — all with barely any delay. A companion mobile app ties everything together, giving security personnel live visualizations and instant notifications right in their hands. Testing showed that the system is accurate, fast, and dependable enough to hold up in real-world conditions — not just in a lab.
Keywords	Crowd Detection, YOLOv8, Deep Learning, Computer Vision, Railway Safety, Real-Time Monitoring.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 7, Issue 2, March-April 2026
Published On	2026-04-30
DOI	https://doi.org/10.63363/aijfr.2026.v07i02.5298

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research