EnviroScan 🌍🤖♻️

🌿 Inspiration

Just as bees 🐝 scan their surroundings for flowers and collect pollen, EnviroScan mimics this natural process by detecting and identifying waste 🗑️ in the environment. Using AI-driven precision 🧠, it guides users to properly dispose of waste, promoting sustainability 🌱 and cleaner communities for all.

🚀 What It Does

EnviroScan is a mobile app that:
✅ Scans waste in real-time using AI-powered object detection.
✅ Identifies materials (plastic 🧴, paper 📄, glass 🍾, etc.) and provides safe disposal guidance.

🛠️ How We Built It

Frontend: Flutter (Dart) for a smooth & intuitive mobile experience.
Backend: FastAPI for processing user-uploaded images.
🧠 AI Model: YOLO segmentation trained on the TACO dataset for waste classification.

⚡ Challenges We Ran Into

🔹 Optimizing YOLO segmentation for mobile efficiency 📲.
🔹 Ensuring smooth communication 🔗 between the frontend and backend.
🔹 Limited dataset variety 📊 requiring data augmentation for higher accuracy.
🔹 Building our first mobile app 📱 – lots of confusing installations 🌀.

🎉 Accomplishments That We're Proud Of

🏆 Finishing the app and successfully connecting the backend.
📱 Creating our first mobile app from scratch!
⚡ Implementing real-time image analysis with AI.
🐝 Incorporating Biomimicry

🤓 What We Learned

🔍 How to optimize AI models for real-time object detection on mobile.
📡 How mobile and backend servers communicate effectively.
🌱 The power of bio-inspired design in solving real-world problems.