What it doesVitaNova: AI-Powered Waste Classification for Recovery Zones Inspiration Inspired by the crisis in Gaza with 37 million tonnes of debris and 85% of waste systems non-operational, we recognized that rebuilding starts with waste management, not construction. Our goal was to democratize waste classification expertise when it's most urgently needed. What it does VitaNova combines computer vision with Perplexity AI to create a waste classification system accessible via smartphone. Users upload images to identify waste types, receive safety guidance, and get practical recycling recommendations—all optimized for conflict zones with limited connectivity. How we built it We trained a model on Google's Teachable Machine for six waste categories, built a mobile-friendly interface, integrated Perplexity API for contextual guidance, and designed the system to serve both communities and relief organizations. Challenges Our main challenges included creating a reliable model with limited training data, optimizing for poor connectivity, ensuring safety-critical information was clear to non-experts, and crafting appropriate AI prompts for relevant guidance. What's next We plan to expand with more waste categories, multi-lingual support, a safety alert network for dangerous materials, offline functionality, and potential robotics integration for safer handling.

Built With

Share this project:

Updates