SLARM Smart Lock and Room Monitoring System

SHIPPED
Updated: Sun Jun 01 2025 00:00:00 GMT+0000 (Coordinated Universal Time) | Started: Sat Mar 01 2025 00:00:00 GMT+0000 (Coordinated Universal Time)

Embedded IoT system combining face recognition, BLE sensor mesh, and secure audit logging for access control and monitoring.

Gallery

8 images
Facial Recognition Demo
SLARM Poster
Raspberry Pi5 for ML

Notes

Overview

SLARM is a secure access control and environmental monitoring system designed for sensitive indoor environments.

Description

The system combines dual factor authentication using CNN based face recognition and a PIN with a BLE sensor mesh for real time environmental monitoring. A Raspberry Pi 5 acts as the central hub, aggregating data from distributed sensor nodes and performing on device anomaly detection using a Kalman filter.

All access events and anomalies are immutably logged using a lightweight custom blockchain to provide auditability without heavy infrastructure. Data is visualised through Grafana dashboards and embedded displays.

SLARM achieved strong real world performance, including a 92 percent authentication success rate and reliable anomaly detection across multiple fault scenarios. The system remained stable during extended operation over a mobile hotspot.

Previous
Fake or Faker
Web based game challenging users to identify Faker among lookalikes and AI generated faces.
Next
TTSWING Player Identification Using Swing Embeddings
Biometric identification of table tennis players using inertial sensor data and learned swing embeddings.