Security · 1h ago
EyeNet Turns Webcam Feed into Structured Security Incidents
EyeNet is a real-time campus surveillance system that processes video through detection, tracking, and severity scoring to generate actionable alerts. It uses YOLOv8 for hazard detection, face recognition, and uniform compliance checks, with ByteTrack to reduce false positives. The system stores events in SQLite with WAL mode and provides a dashboard with SSE updates.
Meridian48 take
While EyeNet demonstrates a thoughtful pipeline for reducing alert noise, its reliance on a single webcam and local SQLite limits scalability for real-world campus deployments.
Read the full reporting
EyeNet: Turning a Webcam Feed Into Actionable Security Incidents →
DEV Community
surveillanceai-security