Viseron

Homeowners and facility operators deploy Viseron to turn standard RTSP and ONVIF security cameras into a self-hosted network video recorder with local AI object detection, face recognition, and license plate reading. Instead of uploading private camera feeds to subscription cloud services, you monitor low-latency WebRTC live streams, scrub through an interactive event timeline, and review 24/7 continuous recordings directly from a responsive web dashboard. You can draw custom detection zones and privacy masks in the visual camera tuning editor to filter out street traffic, while lookback buffering captures footage several seconds before motion or an object triggers an event. Pluggable computer vision pipelines connect your cameras to YOLOv7 Darknet, Google Coral EdgeTPU, CompreFace, dlib, and CodeProject.AI to classify people, vehicles, known faces, and license plates in real time. Tiered storage policies automatically migrate older video segments from fast NVMe drives to high-capacity archival disks based on age and quota rules. Bidirectional MQTT integration and Home Assistant auto-discovery let you toggle cameras on demand, ingest external motion sensors, and dispatch instant snapshot alerts to Telegram or Discord. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Viseron
Viseron
Viseron
Viseron
Viseron
Viseron
Viseron

Benefits

  • Local AI Vision Without Cloud Subscriptions
  • Process object detection, facial recognition, and license plate reading entirely on your own server using YOLO, TensorFlow, CompreFace, or CodeProject.AI without paying monthly per-camera cloud fees.
  • Tiered Storage With Pre-Event Lookback
  • Record 24/7 continuous video across multiple storage tiers that automatically move aging footage from fast SSDs to archival volumes while preserving pre-event lookback buffers before motion occurs.
  • Interactive Web Timeline and Camera Tuning
  • Browse synchronized multi-camera event timelines, stream low-latency WebRTC live video, draw detection zones and masks visually, and hot-reload YAML configuration changes directly from the browser.
  • Native Home Assistant and MQTT Automation
  • Expose camera streams, detected objects, recognized faces, and recording controls automatically to Home Assistant via MQTT discovery while triggering rich snapshot alerts over Telegram and Discord.

Features

  • Multi-Backend Object Detection
  • Run real-time object detection on RTSP camera streams using OpenCV YOLOv3/v4/v7 Darknet, TensorFlow on Google Coral EdgeTPU, or CodeProject.AI inference servers.
  • Face and Plate Recognition
  • Identify known and unknown faces through CompreFace, dlib, or CodeProject.AI, and automatically extract vehicle registration numbers with integrated license plate recognition.
  • Tiered Continuous Recording
  • Configure 24/7 continuous recording alongside event-triggered clips with customizable multi-tier storage retention rules, PostgreSQL event indexing, and direct browser MP4 downloads.
  • Visual Zones and Masking
  • Define polygon detection zones and motion masks in the web-based Camera Tuning interface to restrict AI processing to specific areas and eliminate false alarms.
  • WebRTC Live Multi-Camera Grid
  • View low-latency live camera feeds, pan-tilt-zoom controls for ONVIF Profile S cameras, and responsive event timelines across desktop and mobile browsers.
  • Hot-Reload Web Config Editor
  • Edit config.yaml with built-in syntax validation in the browser and reload modified camera or detector components on the fly without restarting the server.

Apps Similar to Viseron