- Project structure setup
- Repository initialization
- Team role assignment
- Design wireframe
- API research and selection
Deliverable: Organized project structure, clear roles
- A-Frame camera setup
- Basic AR overlay system
- UI controls (feature toggles)
- Camera permission handling
Owner: Frontend Developer
Deliverable: Working camera feed with AR overlay framework
- Web Speech API integration
- Real-time caption display
- AR text positioning
- Timed fade-out animation
Owner: ML Developer + Frontend Developer
Deliverable: Live speech captions visible on camera feed
- MediaPipe Hands integration
- TensorFlow.js model setup
- Basic gesture classification (A-Z subset)
- AR text overlay for signs
Owner: ML Developer
Deliverable: Recognizes a few ASL gestures and displays text
- TensorFlow.js COCO-SSD setup
- Object detection implementation
- Web Speech Synthesis integration
- face-api.js emotion recognition
Owner: ML Developer + UX Lead
Deliverable: Audio narration of scenes and detected objects
- face-api.js integration
- Firebase Firestore setup
- Face embedding storage/retrieval
- AR memory tags for known faces
- Add new face functionality
Owner: ML Developer + Backend Developer
Deliverable: Recognizes saved faces and displays personalized tags
- Feature toggle UI
- Error handling
- Performance optimization
- Accessibility improvements
- Cross-browser testing
Owner: Entire Team
Deliverable: Polished, integrated application
- Demo video recording
- Presentation slides
- Bug fixes
- Final testing
- Deployment
Owner: Entire Team
Deliverable: Working demo and presentation
Current Phase: Setup Complete ✅
Next Steps: Frontend scaffolding