Deep Learning‐Based Safety Helmet Detection in Engineering Management Based on Convolutional Neural Networks

TLDR

Visual inspection and video monitoring are crucial for preventing injuries at construction sites, yet current systems lack real‑time computer‑vision solutions, and existing deep‑learning helmet detectors are mainly tailored to traffic scenes rather than the complex construction environment. This study proposes a deep‑learning approach to detect safety helmet usage in real time on construction sites. The method employs the SSD‑MobileNet architecture trained on a publicly released dataset of 3,261 images collected from on‑site video capture and web‑crawled sources, split into training, validation, and test sets in an 8:1:1 ratio. Experiments show the SSD‑MobileNet model accurately and efficiently identifies workers not wearing helmets, demonstrating satisfactory performance for real‑time safety monitoring.

Abstract

Visual examination of the workplace and in‐time reminder to the failure of wearing a safety helmet is of particular importance to avoid injuries of workers at the construction site. Video monitoring systems provide a large amount of unstructured image data on‐site for this purpose, however, requiring a computer vision‐based automatic solution for real‐time detection. Although a growing body of literature has developed many deep learning‐based models to detect helmet for the traffic surveillance aspect, an appropriate solution for the industry application is less discussed in view of the complex scene on the construction site. In this regard, we develop a deep learning‐based method for the real‐time detection of a safety helmet at the construction site. The presented method uses the SSD‐MobileNet algorithm that is based on convolutional neural networks. A dataset containing 3261 images of safety helmets collected from two sources, i.e., manual capture from the video monitoring system at the workplace and open images obtained using web crawler technology, is established and released to the public. The image set is divided into a training set, validation set, and test set, with a sampling ratio of nearly 8 : 1 : 1. The experiment results demonstrate that the presented deep learning‐based model using the SSD‐MobileNet algorithm is capable of detecting the unsafe operation of failure of wearing a helmet at the construction site, with satisfactory accuracy and efficiency.