Enhancing the Safety of the Workplace Using Raspberry Pi Powered reTerminal DM

Project Summary:

The PPE detection system is a vital component in enhancing workplace safety, particularly in the construction sector where ensuring the well-being of the workforce is critical for both employee health and production efficiency. In the civil engineering industry, safety is a non-negotiable constraint. Given the challenging task of individually inspecting workers in construction, our solution involves a real-time detection system to ascertain whether essential Personal Protective Equipment (PPE) is being worn. This not only streamlines safety procedures but also provides timely instructions to workers, ensuring compliance and fostering a safer and more efficient work environment.

Key Info

Seeed’s solutionRaspberry Pi-powered HMI  reTerminal DM
Industry: Civil Engineering Construction Fields
Software: Raspbian OS (Bullseye Version), TensorFlow Lite Library, Open CV Library )


The challenge is to improve the accuracy of real-time entrance monitoring in construction areas, where relying solely on human observation may lead to oversight of individuals not wearing essential safety gear. This oversight can result in significant direct costs like medical bills, equipment damage, litigation, and regulatory fines, as well as indirect costs such as expenses for hiring replacement workers, missed deadlines penalties, and corrective measure implementation. To address this, there is a need for a cost-effective and versatile system that can concurrently handle networking tasks while performing real-time PPE detection. The deployment of such a multifunctional device has the potential to enhance accuracy and efficiency, reducing the overall impact of safety lapses in construction environments.


The solution involves the implementation of a highly effective Raspberry Pi-powered reTerminal DM with a built-in camera at the entrance of the construction site. This setup provides an ideal solution for real-time monitoring, as it enables the system to capture and analyze individuals entering the site. To ensure the correct usage of Personal Protective Equipment (PPE), a civil construction guard is stationed at the entrance, leveraging the power of the YOLOv5n deep neural network architecture in TFLite version. This configuration, optimized for Raspberry Pi-powered reTerminal DM, achieves an impressive performance of 10 frames per second (FPS). Furthermore, by incorporating a Coral TPU, the system can achieve an enhanced speed of 20 FPS.

This innovative solution proves essential during morning and lunch hours, precisely when enforcing safety protocols is critical. Beyond its primary function, the reTerminal DM is repurposed for inventory management in the construction field after these crucial safety monitoring periods. This dual-functionality showcases the versatility and efficiency of the system, providing a comprehensive approach to both safety enforcement and logistical management in construction operations.

Seeed Studio’s Raspberry Pi Ecosystem

Seeed Studio has been serving the Raspberry Pi user community since 2013 and took the lead to join the approved reseller and design partner. Since the first version of reTerminal in 2021, we have a series of products including reRouteredge controller series, and this year reTerminal DM, serving creators, makers, enthusiasts, students, engineers, enterprises as well as industries, and every scenario needing Raspberry Pi. 

More Resources

About Author


December 2023