Air-gapped multi-camera surveillance platform with real-time threat detection across 40+ feeds for a classified defence installation.
At a glance
Built with
Overview
A classified government client required a perimeter intelligence system capable of detecting, classifying, and alerting on threats across 40+ concurrent camera feeds — entirely offline, with zero cloud dependency.
The Challenge
The system had to operate in an air-gapped LAN environment with no internet access. All AI inference had to run on-premise on hardened GPU hardware, with false-positive rates below 0.3% to avoid alert fatigue in a high-stakes operational context.
How it fits together
Architecture
The Solution
We deployed a YOLOv8x detection pipeline optimised for edge inference on NVIDIA A100 clusters, trained on the installation's own camera feeds. A React control-room dashboard delivered real-time alerts, camera management, and audit trails — all on an isolated intranet.
Results
From brief to production