Resource-Aware Object Detection and Recognition Using Edge AI Across the Edge-Fog Computing Continuum

Dragan Stojanović¹, Stefan Sentić¹, Natalija Stojanović¹ and Teodora Stamenković¹

Faculty of Electronic Engineering, University of Niš
Aleksandra Medvedeva 14, 18000 Niš
dragan.stojanovic@elfak.ni.ac.rs, stefan.sentic@elfak.rs, natalija.stojanovic@elfak.ni.ac.rs, teodora.stamenkovic@elfak.rs

Abstract

Edge computing and edge intelligence have gained significant traction in recent years due to the proliferation of Internet of Things (IoT) devices, the exponential growth of data generated at the network edge, and the demand for real-time and context-aware applications. Despite its promising potential, the application of Artificial Intelligence (AI) on the edge faces many challenges, such as edge computing resource constraints, heterogeneity of edge devices, scalability issues, security and privacy concerns, etc. The paper addresses the challenges of deploying deep neural networks (DNNs) for edge intelligence and traffic object detection and recognition on a video captured by edge device cameras. The primary aim is to analyze resource consumption and achieve resource-awareness, optimizing computational resources across diverse edge devices within the edge-fog computing continuum while maintaining high object detection and recognition accuracy. To accomplish this goal, a methodology is proposed and implemented that exploits the edge-to-fog paradigm to distribute the inference workload across multiple tiers of the distributed system architecture. The edge-fog related solutions are implemented and evaluated in several use cases on datasets encompassing real-world traffic scenarios and traffic objects’ recognition problems, revealing the feasibility of deploying DNNs for object recognition on resource-constrained edge devices. The proposed edge-to-fog methodology demonstrates enhancements in recognition accuracy and resource utilization, validating the viability of both edge-only and edge-fog based approaches. Furthermore, experimental results demonstrate the system’s adaptability to dynamic traffic scenarios, ensuring real-time recognition performance even in challenging environments.

Key words

Resource awareness, Traffic Object Recognition, Edge AI, Distributed Neural Networks, Edge-Fog Computing Continuum

Full text

Download Available in PDF
Portable Document Format

How to cite

Stojanović, D., Sentić, S., Stojanović, N., Stamenković, T.: Resource-Aware Object Detection and Recognition Using Edge AI Across the Edge-Fog Computing Continuum. Computer Science and Information Systems