Helmet Detection Computer Vision Model - A machine learning project that detects helmets in images and video streams using convolutional neural networks. Includes Jupyter Notebook implementations for model training and evaluation, Python utilities for inference, and Docker configuration for containerized deployment.

Deep learning image classifier that detects whether construction workers are wearing hard hats. Built with PyTorch and ResNet18 transfer learning — frozen backbone training then fine-tuning. Achieves 94.6% validation accuracy. Includes Streamlit web app for real-time predictions on uploaded images.

A real-time AI computer vision system that detects safety helmet violations and automatically logs evidence to the cloud. Built with Python, Flask, YOLOv8, and Azure Blob Storage.

Custom Safety Zone for AMR

A non-invasive public safety detection system is a systematic, accurate system that empowers various organizations to create safer environments by permitting only healthy and precautious individuals.

Detects7 is a lightweight object-detection demo built using YOLOv8, featuring a FastAPI backend and a React + Vite frontend. Trained on the Falcon synthetic dataset, it identifies seven safety-related object classes and includes tools for training, evaluation, visualization, and local deployment.