Hardhat App

A real-time hardhat detection application that uses a YOLOv8 object detection model to identify whether construction workers are wearing safety helmets.

Model used: YOLOv8m Hard Hat Detection via Ultralytics.

Table of Contents

• Features
• Tech Stack
• Results
• Installation
  • Backend (FastAPI)
  • Frontend (Next.js)
• Usage
• API
• Contributing
• License

---

Features

• Detects hard hats in uploaded images or via camera feed.
• Returns bounding boxes and classification results.
• FastAPI backend serving the detection model.
• Next.js frontend for intuitive user interface.
• Support for multiple image formats (JPEG, PNG, WebP).

---

Tech Stack

• Frontend: Next.js, React, Tailwind CSS
• Backend: FastAPI, Python 3.10+
• ML Model: YOLOv8 (Ultralytics)
• Deployment: Hugging Face Hub (for model), Docker-ready

---

Results

Sample outputs from the hardhat detection application are available in the Results/ directory:

• initial-image.jpeg - Original test image
• annotated-image.png - Annotated output with detected helmets highlighted on the frontend dashboard
• ppe_safety_report.pdf - Detailed analysis report

---

Installation

Backend (FastAPI)

Install uv by Astral: https://docs.astral.sh/uv/getting-started/installation/

install dependencies and run the backend with:

uv run fastapi dev

The backend will be available at http://localhost:8000.

---

Frontend (Next.js)

Navigate to the frontend directory:

cd ../frontend

Install dependencies:

npm install

Start the development server:

npm run dev

The frontend will be available at http://localhost:3000.