Skip to content

shruthey/Guard-AI

Repository files navigation

Guard AI

Overview

Guard AI is an application designed to enhance safety by using machine learning to identify objects that may pose hazards in various environments. The app aims to provide users with real-time information about potential dangers and suggestions on how to proof or secure these objects to prevent accidents.

Features

Object Identification

Guard AI utilizes a machine learning model to accurately identify objects within its scope. The model has been trained on a diverse dataset to recognize common household, workplace, and outdoor items.

Hazard Assessment

Once an object is identified, the app assesses its potential hazard level based on various factors such as size, location, and context. The hazard assessment is designed to prioritize objects that may pose an immediate threat to safety.

Proofing Recommendations

Guard AI not only identifies hazards but also provides users with practical recommendations on how to proof or secure the identified objects. This may include suggestions for proper storage, installation of safety devices, or relocation of items to safer locations.

Getting Started

Installation

To install Guard AI, follow these steps:

  1. Clone the repository: git clone https://github.com/your-username/Guard-AI.git
  2. Navigate to the project directory: cd frontend
  3. Install dependencies: npm install

Usage

  1. Open the Guard AI app on your device.
  2. Upload a pre recorded video to our website.
  3. Receive real-time feedback on identified hazards and proofing recommendations.

Contributing

We welcome contributions from the community. If you find a bug, have a feature request, or would like to contribute in any way, please open an issue or submit a pull request.

License

This project is licensed under the MIT License.

Contact

For any inquiries, please contact the development team at [email protected].

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published