yolo model Safety Helmet detection in construction scenes

Project Code :TCPGPY1814

Objective

The primary objective of this project is to develop an AI-powered helmet detection system using YOLOv8 that can accurately and efficiently identify the presence or absence of safety helmets on workers in construction environments. The key goals include. Automated Helmet Detection: Implement a deep learning-based object detection model capable of identifying helmets in real-time across varying lighting, backgrounds, and sangles.

Abstract

Ensuring safety compliance on construction sites is critical to reducing workplace hazards. This project introduces an intelligent helmet detection system using the YOLOv8 (You Only Look Once, version 8) object detection algorithm to identify whether workers are wearing safety helmets in real-time. The system is designed for deployment in construction environments to enhance on-site safety monitoring through automated video surveillance. Leveraging the high accuracy and speed of YOLOv8, the model can effectively detect helmet presence in complex and dynamic scenes. The application is built using a Flask-based Python backend and a responsive front-end interface developed with HTML, CSS, and JavaScript. This lightweight and scalable solution offers real-time alerts and visual feedback, aiding construction managers in ensuring regulatory compliance and preventing accidents. The proposed system is suitable for integration with CCTV feeds or on-site monitoring setups, offering a cost-effective tool for occupational safety enforcement.

Keywords: Helmet Detection, YOLOv8, Construction Safety, Flask, Object Detection, Computer Vision.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.