Skip to content

n-donati/GreenGuard

 
 

Repository files navigation

GreenGuard 🌱

Introduction

GreenGuard is an innovative solution designed to address one of the most pressing issues in the agricultural industry: crop disease. By leveraging advanced technologies, GreenGuard aims to prevent plant diseases and promote a quality-based system that enhances business in the agricultural sector.

Our inspiration came from real-world experiences in the agricultural industry, where late disease detection often leads to significant crop losses. According to the Mexican government, around ten thousand tons of crops are lost annually. GreenGuard seeks to mitigate these losses and optimize harvest yields.

Features

  • AI-Powered Crop Health Monitoring: Utilizes an advanced AI model optimized through OpenVino for accurate disease detection.
  • Dashboard: Provides a user-friendly, personalized interface for monitoring greenhouse health.
  • Historical Data Analysis: Incorporates past data to offer insights and predict potential issues.
  • Evidence-Based Certification: Helps producers connect with buyers by certifying product quality.
  • Business Networking: Facilitates connections between producers and buyers in the agricultural sector.

Technology Stack

  • Machine Learning: TensorFlow, OpenVino
  • Backend: Django
  • Cloud Infrastructure: Google Cloud Platform (GCP)
  • Containerization: Docker
  • Image Processing: Pillow
  • Process Monitoring: Softtek's Frida
  • Database: PostgreSQL, SQLite
  • Frontend: HTML, CSS, JavaScript
  • Additional Technologies: Cloud Storage

Usage

https://greenguard.com.mx

Challenges

During the development of GreenGuard, we encountered several challenges:

  1. Adapting deep learning models to diverse dataset layouts.
  2. Time-consuming model training and OpenVino integration.
  3. Navigating extensive cloud documentation.
  4. Integrating various components into a cohesive software solution.

Future Plans

We are committed to the continued development of GreenGuard. Our future plans include:

  1. Adding new features and refining existing ones.
  2. Developing more powerful deep learning models with near-perfect accuracy.
  3. Expanding the project's scope to make a significant impact on optimal crop harvesting and the agricultural sector.

Preview

image image image image

About

HACKMTY 2024 PROJECT SECOND PLACE

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • JavaScript 45.5%
  • HTML 37.9%
  • Python 12.9%
  • Jupyter Notebook 3.3%
  • Other 0.4%