Towards Edge-Cloud Architectures for Personal Protective Equipment Detection

TL;DR

This paper proposes an architecture for real-time detection of personal protective equipment, specifically safety helmets, using edge-cloud and edge-only deployment, tested on a construction site within the scope of the ASSIST-IoT project.

Contribution

It introduces a deployable architecture for PPE detection that supports both edge-only and edge-cloud setups, demonstrating feasibility with YOLOX-based helmet counting.

Findings

Edge-only deployment is feasible with available hardware.

Preliminary results show successful live PPE detection.

Future work will analyze performance differences between architectures.

Abstract

Detecting Personal Protective Equipment in images and video streams is a relevant problem in ensuring the safety of construction workers. In this contribution, an architecture enabling live image recognition of such equipment is proposed. The solution is deployable in two settings -- edge-cloud and edge-only. The system was tested on an active construction site, as a part of a larger scenario, within the scope of the ASSIST-IoT H2020 project. To determine the feasibility of the edge-only variant, a model for counting people wearing safety helmets was developed using the YOLOX method. It was found that an edge-only deployment is possible for this use case, given the hardware infrastructure available on site. In the preliminary evaluation, several important observations were made, that are crucial to the further development and deployment of the system. Future work will include an in-depth investigation of performance aspects of the two architecture variants.