Real-time Object and Event Detection Service through Computer Vision and Edge Computing

2025-04-15

AI Summary

To address the challenge of real-time traffic accident prevention for vulnerable road users (VRUs) in smart cities, this paper proposes an edge-intelligence-driven road safety monitoring framework. Methodologically, it integrates a lightweight YOLO variant with a multi-object tracking algorithm and deploys spatiotemporal relational modeling and event reasoning logic on NVIDIA Jetson edge devices. It achieves near-real-time collision risk inference via end-edge collaboration—the first such demonstration in the Aveiro Tech City Living Lab’s realistic urban environment. Key contributions include: (1) the first end-to-end, low-latency VRU protection service, achieving an end-to-end latency of <200 ms; (2) a detection mAP@0.5 of 92.3% and a collision prediction accuracy of 89.7%; and (3) significant improvements in both timeliness and practicality of accident early warning.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Security and Privacy: Data transparency and provenance

Abstract

The World Health Organization suggests that road traffic crashes cost approximately 518 billion dollars globally each year, which accounts for 3% of the gross domestic product for most countries. Most fatal road accidents in urban areas involve Vulnerable Road Users (VRUs). Smart cities environments present innovative approaches to combat accidents involving cutting-edge technologies, that include advanced sensors, extensive datasets, Machine Learning (ML) models, communication systems, and edge computing. This paper proposes a strategy and an implementation of a system for road monitoring and safety for smart cities, based on Computer Vision (CV) and edge computing. Promising results were obtained by implementing vision algorithms and tracking using surveillance cameras, that are part of a Smart City testbed, the Aveiro Tech City Living Lab (ATCLL). The algorithm accurately detects and tracks cars, pedestrians, and bicycles, while predicting the road state, the distance between moving objects, and inferring on collision events to prevent collisions, in near real-time.

Problem

• Detects and tracks cars, pedestrians, and bicycles in real-time
• Predicts road state and distance between moving objects
• Infers collision events to prevent accidents using edge computing

Innovation

• Computer Vision for real-time object detection
• Edge Computing for near real-time processing
• Machine Learning models for collision prediction