An IoT-Driven Intrusion Detection and Autonomous UAV Surveillance System with Edge-AI Verification

Abstract: Traditional home and commercial security systems relying solely on static CCTV cameras are highly vulnerable to physical tampering, often resulting in critical surveillance blind spots during targeted intrusions. Furthermore, conventional alarms suffer from high false-positive rates, leading to alarm fatigue. This paper proposes a robust, Internet of Things (IoT) driven, multi-layered security framework designed to provide uninterrupted monitoring through autonomous robotic response. At the core of the architecture, a localized edge-computing Ground Control Station (Laptop GCS) processes real-time video feeds, executing deep-learning algorithms for facial recognition and continuous pixel-variance analysis to mathematically detect sudden camera blackouts. In the event of a compromised camera, the system initiates a distributed, dual-tier response mechanism. Bypassing vulnerable local networks, the GCS publishes a low-latency execution payload to a secure HiveMQ Cloud MQTT broker. An Unmanned Aerial Vehicle (UAV), equipped with an onboard Raspberry Pi 5 companion computer and a Pixhawk flight controller, intercepts this payload, activates onboard hardware deterrents, and launches into an autonomous waypoint patrol, restoring visual oversight via a 5.8GHz analog video transmitter. Crucially, the system employs a secondary artificial intelligence verification loop; the GCS scans the incoming aerial feed for human silhouettes. Using adaptive decision-making, the system routes a high- priority alert and live video stream to a custom Flutter mobile application only upon visually confirming a human threat. Experimental results demonstrate a visual feed restoration time of under 14 seconds and near-zero false positives, providing a cost-effective, intelligent framework for next-generation smart security systems.

Keywords: Intrusion detection, Autonomous UAV, Edge Computing, MQTT, HOG algorithm, False-alarm mitigation, Smart home security.