Skip to content

Johnaaron0108/CNN_Helmet_Pred

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

4 Commits
Β 
Β 
Β 
Β 

Repository files navigation

Helmet Detection πŸͺ–


πŸ“Œ Overview

Detect helmets in real-time from images or video streams using Convolutional Neural Networks (CNNs).
This project is aimed at improving safety monitoring in industrial and construction environments.


πŸ› οΈ Features

  • CNN-based helmet detection
  • Bounding box predictions for head regions
  • Real-time video stream analysis
  • Dataset augmentation for improved model robustness
  • Simple integration for CCTV or webcam feeds

πŸ“¦ Installation / Setup

  1. Clone the repository
git clone https://github.com/Johnaaron0108/CNN_Helmet_Pred.git
cd CNN_Helmet_Pred

About

This CNN model detects helmets in images using six convolutional layers with batch normalization and max pooling, followed by dense layers with Elastic Net regularization and dropout. It processes 64x64 RGB images and outputs a binary prediction (helmet or no helmet). Data augmentation and optional bounding box cropping improve training robustness.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors