AI Home Security Camera

A Raspberry Pi 5 + Sony IMX500 security system with on-device face recognition, local AI scene descriptions, and full control from Telegram — no cloud AI, no subscription.

Hardware & Software

The system runs on a Raspberry Pi 5 paired with the Raspberry Pi AI Camera — a Sony IMX500 sensor with its own on-chip neural network accelerator. Person detection and pose estimation happen directly on the sensor; face recognition and scene analysis run on the Pi's CPU, entirely offline.

Board
Raspberry Pi 5 (8GB)
Camera
Sony IMX500 AI Camera
Person Detection
On-Sensor NN (SSD MobileNetV2)
Face Recognition
YuNet + SFace
Scene AI
llava-phi3 via Ollama (local)
Pose Estimation
HigherHRNet, 17 keypoints
Control
Telegram Bot (30+ commands)
Live Stream
MJPEG over ngrok, password-protected
Alerts
GPIO buzzer + Telegram burst photos
Built by
Schematrix

What It Actually Does

One camera, two modes, all controlled from a phone:

01

Face Recognition

Guided 3-angle enrollment, then silent logging for known faces and instant alerts for strangers.

02

AI Scene Description

Send /scene and a local vision model describes what's happening, using the recognized person's name.

03

Stranger Alerts

Burst photos to Telegram and an optional GPIO siren when an unrecognized face is confirmed.

04

Pose / Skeleton Mode

Switch to IMX500 HigherHRNet pose estimation — 17-keypoint skeletons and basic action classification.

05

Live Streaming

Password-protected MJPEG stream over ngrok, viewable from any browser, anywhere.

06

Quiet Hours

Scheduled or manual quiet hours mute the siren while Telegram alerts keep coming through.

See It Running

A walkthrough of the system in action — face recognition, alerts, and live scene analysis.