How oxm-tech/oxm-vision works
OXM Vision is a Jetson-based, multi-camera surveillance application. Its runtime captures CSI and USB video plus USB audio; analyzes frames and audio for objects, faces, falls, speech, and keywords; correlates events; persists them; and serves live views, search, and reports through a web dashboard. The main processing and orchestration responsibilities are concentrated in src/main.py; supporting modules implement CSI capture, face identity, pose analysis, event storage, and dashboard behavior. README capabilities not visible in the sampled excerpts are included where documented; their internal wiring is not asserted.
Main entry points: main.py Event correlation · dashboard.py Web dashboard · face_reid.py Face re-identification · csi_worker.py CSI capture worker
Components 20
Input capture
- CSI capture worker
src/csi_worker.py - Video capture
src/main.py - Audio capture
src/main.py
Detection and analysis
- Object detection
src/main.py - Audio classification
src/main.py - Speech transcription
src/main.py - Face re-identification
src/face_reid.py - Fall detection
src/pose.py
Events and identity
- Event correlation
src/main.py - SQLite event store
src/db.py - Face embedding store
src/face_reid.py - Face enrollment
src/enroll_live.py
Dashboard and reporting
- Web dashboard
src/dashboard.py - PDF daily report
src/dashboard.py
Other components
- Operator
- CSI camera
- USB camera
- USB audio
- Telegram
- LLM service
Connections 24
- CSI camera → CSI capture worker: provides frames
README.md - CSI capture worker → Video capture: streams frames
src/main.py - USB camera → Video capture: provides frames
src/main.py - USB audio → Audio capture: provides audio
README.md - Video capture → Object detection: analyzes frames
src/main.py - Video capture → Face re-identification: queues frames
src/main.py - Video capture → Fall detection: analyzes poses
README.md - Audio capture → Audio classification: classifies audio
src/main.py - Audio capture → Speech transcription: transcribes speech
README.md - Object detection → Event correlation: emits detections
src/main.py - Face re-identification → Event correlation: emits identities
src/main.py - Fall detection → Event correlation: emits fall events
src/main.py - Audio classification → Event correlation: emits audio events
src/main.py - Speech transcription → Event correlation: correlates speech
src/main.py - Event correlation → SQLite event store: writes events
src/main.py - Face re-identification → Face embedding store: loads and saves
src/face_reid.py - Face enrollment → Face embedding store: updates embeddings
src/enroll_live.py - Operator → Face enrollment: enrolls person
README.md - Operator → Web dashboard: views surveillance
README.md - Web dashboard → SQLite event store: queries events
src/dashboard.py - Web dashboard → PDF daily report: requests report
README.md - PDF daily report → Telegram: sends report
README.md - Web dashboard → LLM service: queries chat
README.md - Event correlation → Telegram: sends alerts
README.md