Safety helmet wearing plays a major role in protecting the safety of workers in industry and construction, so a real-time helmet wearing detection technology is very necessary. This paper proposes an improved YOLOv4 algorithm to achieve real-time and efficient safety helmet wearing detection. The improved YOLOv4 algorithm adopts a lightweight network PP-LCNet as the backbone network and uses deepwise separable convolution to decrease the model parameters. Besides, the coordinate attention mechanism module is embedded in the three output feature layers of the backbone network to enhance the feature information, and an improved feature fusion structure is designed to fuse the target information. In terms of the loss function, we use a new SIoU loss function that fuses directional information to increase detection precision. The experimental findings demonstrate that the improved YOLOv4 algorithm achieves an accuracy of 92.98%, a model size of 41.88 M, and a detection speed of 43.23 pictures/s. Compared with the original YOLOv4, the accuracy increases by 0.52%, the model size decreases by about 83%, and the detection speed increases by 88%. Compared with other existing methods, it performs better in terms of precision and speed.

In the Industry 4.0 era, with the continuous integration of industrial field systems and upper-layer facilities, interconnection between industrial wireless sensor networks (IWSNs) and industrial Internet networks is becoming increasingly pivotal. However, when deployed in real industrial scenarios, IWSNs are often connected to legacy control systems, through some wired industrial network protocols via gateways. Complex protocol translation is required in these gateways, and semantic interoperability is lacking between IWSNs and the industrial Internet. To fill this gap, our study focuses on realizing the interconnection and interoperability between an IWSN and the industrial Internet. The Open Platform Communications Unified Architecture (OPC UA) and joint publish/subscribe (pub/sub) communication between the two networks are used to achieve efficient transmission. Taking the Wireless Networks for Industrial Automation Process Automation (WIA-PA), a typical technology in IWSNs, as an example, we develop a communication architecture that adopts OPC UA as a communication bridge to integrate the WIA-PA network into the industrial Internet. A WIA-PA virtualization method for OPC UA pub/sub data sources is designed to solve the data mapping problem between WIA-PA and OPC UA. Then, the WIA-PA/OPC UA joint pub/sub transmission mechanism and the corresponding configuration mechanism are designed. Finally, a laboratory-level verification system is implemented to validate the proposed architecture, and the experimental results demonstrate its promising feasibility and capability.

Face recognition has become very challenging in unconstrained conditions due to strong intra‐personal variations, such as large pose changes. Face normalisation can help to resolve these problems and effectively improve the face recognition performance in unconstrained conditions by converting non‐frontal faces to frontal ones. However, there are other complex facial variations in addition to pose, such as illumination and expression, which will also influence face recognition performance. The authors propose a well‐designed generative adversarial network‐based multi‐factor joint normalisation network (MFJNN) to normalise multiple factors simultaneously. First, a multi‐encoder generator and a feature fusion strategy are designed and implemented in the MFJNN to realise the joint normalisation of multiple factors in addition to pose. Second, a convolutional neural network‐based (CNN‐based) network is applied in the MFJNN, which allows the MFJNN to simultaneously realise image synthesis and facial representation learning. Moreover, an identity perceptive loss is introduced based on the CNN‐based network to produce reliable identity‐preserving features of the input face images. The experimental results demonstrate that the proposed method can synthesise multi‐factor normalisation results with identity preservation and effectively improve the face recognition performance.