EdgeAware: Distributed Threat Detection and Monitoring System for Smart Cities

Abstract

EdgeAware is a distributed threat detection and monitoring system designed for smart-city applications where quick and coordinated actions are required for public safety and infrastructure management. Traditional city monitoring systems often rely on centralized processing and single threat event processing, and it can suffer from high latency, heavy bandwidth usage, limited scalability, and reduced reliability under real-world variability such as different viewpoints and domains. Many academic prototypes lack operational support for validation of event and multi-event monitoring. To address these gaps, EdgeAware integrates edge computing with a centralized monitoring workflow. The system demonstrates two multi-view object detection models for the detection of accident and pothole events, trained on YOLOv11s architecture using diverse perspective images from dashcam, drones, and surveillance system. It improves generalization across different domains and viewpoints. For edge deployment, models are converted to TensorFlow Lite and executed in an Android application that performs real-time inference on live camera streams. The app supports IoU-based tracking to filter duplicate detections, enabling event-level reporting. It transmits only representative frame per unique event, encrypted together with metadata and location information for secure and bandwidth-efficient communication. A backend platform is used for ingesting the events and providing a monitoring dashboard with visualization using Here Maps. This is for administrative validation and coordination with response teams such as police, ambulance, and road maintenance teams.

The experimental results have also shown good quality in the detection aspect, with [email protected] at 93.7%, as well as good precision and recall for the models. The edge pipeline also resulted in an average time of approximately 90 ms and a runtime end-to-end latency of 1.5 s, as well as a reduced storage footprint through compression.