How paavansirivardhan123/visiona works
Visiona AI is a hands-free assistive navigation application. Camera frames pass through perception and motion analysis; detections are prioritized and converted into spoken guidance and proximity alerts. In parallel, push-to-talk commands reach an LLM tool router for scene-memory, goal-search, and walking-directions tasks. The README documents broader capabilities, including custom object recognition and multi-camera operation. Edges are limited to relationships shown by sampled source, SOURCE INDEX references, or README statements; several documented subsystems have only directory-level paths because their implementation was not sampled.
Main entry points: main.py Application loop · vision.py Detection pipeline · vision_tools.py Assistant tools · tracker.py Object tracking
Components 24
Capture and orchestration
- Application loop
main.py - Runtime settings
core/config.py
Spatial perception
- Detection pipeline
perception/vision.py - Monocular depth
perception/mono_depth.py - Object tracking
perception/tracker.py - Depth filtering
kinematics/kalman.py - User motion
perception/egomotion.py - Object speed
kinematics/speed.py - Collision timing
kinematics/ttc.py - Spatial records
core/detection.py
Threat and audio guidance
- Threat priority
core/priority_queue.py - Message grouping
kinematics/heatmap.py - Speech output
audio/speech.py - Proximity beeps
audio/alert.py
Voice and reasoning
- Push-to-talk
audio/voice_input.py - Reasoning router
agents/orchestrator.py - Assistant tools
agents/tools/vision_tools.py - Custom recognition
core/recognition.py
Memory and navigation
- Visual memory and goals
core/memory.py - Walking directions
services/google_maps.py - Object signatures
services/vector_db.py
Other components
- User
- Camera feeds
- Google Maps API
Connections 26
- User → Push-to-talk: speaks commands
README.md - Camera feeds → Application loop: provide frames
README.md - Application loop → Detection pipeline: processes frames
main.py - Application loop → Runtime settings: reads settings
main.py - Detection pipeline → Monocular depth: estimates distance
perception/vision.py - Detection pipeline → Object tracking: tracks detections
perception/vision.py - Object tracking → Depth filtering: filters depth
perception/tracker.py - Detection pipeline → User motion: estimates user motion
perception/vision.py - Detection pipeline → Object speed: estimates speed
perception/vision.py - Detection pipeline → Collision timing: computes collision time
perception/vision.py - Detection pipeline → Spatial records: creates records
perception/vision.py - Application loop → Threat priority: prioritizes detections
main.py - Application loop → Message grouping: builds guidance
main.py - Application loop → Speech output: queues speech
main.py - Application loop → Proximity beeps: triggers alerts
main.py - User → Application loop: operates interface
README.md - Application loop → Push-to-talk: captures speech
main.py - Application loop → Reasoning router: routes commands
main.py - Reasoning router → Assistant tools: dispatches tools
agents/orchestrator.py - Application loop → Custom recognition: uses recognition
main.py - Application loop → Visual memory and goals: updates and checks
main.py - Assistant tools → Visual memory and goals: reads and updates
agents/tools/vision_tools.py - Assistant tools → Walking directions: requests route
agents/tools/vision_tools.py - Assistant tools → Object signatures: queries signatures
agents/tools/vision_tools.py - Walking directions → Google Maps API: fetches directions
services/google_maps.py - Speech output → User: speaks guidance
README.md