The main objectives of this project are to enhance crowd safety during Hajj by detecting abnormal human behaviors in real-time usingYOLOv8.It focuses on applying deep learning techniques to identify potentially dangerous situations like falls, fights, or stampedes. The goal is to support quick decision-making and ensure timely response for preventing crowd-related disasters.
This project presents a real-time crowd safety monitoring system using Raspberry Pi, USB web camera, speaker, buzzer, red LED, and the YOLOv8 deep learning model. The system continuously analyzes live video streams to detect abnormal activities, physical fights, and crowd congestion in crowded environments. When an abnormal event is detected, the buzzer and speaker generate warning alerts, while the red LED provides a visual indication of the emergency. The proposed system offers a low-cost, portable, and efficient solution for enhancing crowd safety, improving emergency response, and supporting intelligent crowd management in large public gatherings such as Hajj, religious events, and transportation hubs.
Keywords: Keywords: YOLOv8, Crowd Safety, Abnormal Behavior Detection, Raspberry Pi.
NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Hardware components:
Software requirements: