Industrial Internet of Things (IIoT) has been widely applied in smart home, smart city and smart traffic, etc. It is a big challenge to recognize facial expression of IIoT systems more effectively. In order to overcome this difficulty, we propose a parallel neural network combining texture features, which can be applied in facial expression recognition. This parallel neural network is constructed by convolution neural network, residual network, and capsule network. Additionally, texture analysis is conducted on facial expression images to extract abundant features. Eight texture features are extracted by Gray-level Co-occurrence Matrix (GLCM) and integrated with features of original images. Finally, these integrated features extracted by three kinds of networks are used to classify facial images. Experimental results prove the proposed approach has a high recognition rate and strong robustness compared to competitive algorithms. The idea in combination with texture features also provides a new solution for the image classification.

In recent years, underwater wireless sensor networks (UWSN) have received extensive attention due to their application in the development of marine resources. The underwater acoustic channel has long delay, low bandwidth and highly dynamic changes in the underwater environment, so that the existing technologies and protocols in the traditional wireless sensor network (WSN) cannot be directly applied to underwater. This paper studies the MAC protocol and positioning technology of underwater wireless sensor networks, and introduces the typical underwater line sensor network MAC protocol. Aiming at the problem of spatial fairness caused by the propagation characteristics of underwater acoustic channel and the triple terminal problem caused by long propagation delay in underwater wireless sensor networks, and effectively implementing the multi-channel mechanism, an underwater multi-channel based on single transceiver is proposed, which is SFM-MAC. The existing underwater positioning algorithms are divided into two categories, centralized positioning algorithm and distributed positioning algorithm, and each type of algorithm is briefly explained. In this paper, the Markov chain is used to construct the reservation model of the control channel, and the theoretical analysis of multi-channel throughput is given. The theoretical throughput of the multi-channel MAC protocol under the condition of reserved collision is obtained. Finally, the article verifies the actual performance of SFM-MAC through simulation experiments.

Multiple object tracking based on tracking-by-detection is the most common method used in addressing illumination change and occlusion problems. In this paper, we present a tracking algorithm based on Edge Multi-channel Gradient Model. We first use the canny operator to extract the edges of the image, and establish a biologically inspired Multi-channel Gradient Model that integrate the spatio-temporal-spectral information of the edge to detect moving multiple objects. Under this model, the ORB feature is introduced to solve the problem of matching the object with the object library. Therefore, we can achieve object consistency, and the threshold classification method can solve the problem of multiple object occlusion in the process of persistent multiple object tracking. The experimental results show that the proposed method can effectively deal with the problems of occlusion and illumination changes. Compared with other state-of-the-art algorithms, the proposed algorithm achieves better performance on MOTA, MOTP, and IDF1. In particular, it performs best on IDSW on MOT2015 dataset, with an average improvement ratio of 28.99% over the second-place algorithm. In addition, our algorithm has a better performance in running time, achieving a good compromise between the speed and the accuracy.

Accident detection using Closed Circuit Television (CCTV) footage is one of the most imperative features for enhancing transport safety and efficient traffic control. To this end, this research addresses the issues of supervised monitoring and data deficiency in accident detection systems by adapting excellent deep learning technologies. The motivation arises from rising statistics in the number of car accidents worldwide; this calls for innovation and the establishment of a smart, efficient and automated way of identifying accidents and calling for help to save lives. Addressing the problem of the scarcity of data, the presented framework joins Generative Adversarial Networks (GANs) for synthesizing data and Convolutional Neural Networks (CNN) for model training. Video frames for accidents and non-accidents are collected from YouTube videos, and we perform resizing, image enhancement and image normalisation pixel range adjustments. Three models are used: CNN, Fine-tuned Convolutional Neural Network (FTCNN) and Vision Transformer (VIT) worked best for detecting accidents from CCTV, obtaining an accuracy rate of 94% and 95%, while the CNN model obtained 88%. Such results show that the proposed framework suits traffic safety applications due to its high real-time accident detection capabilities and broad-scale applicability. This work lays the foundation for intelligent surveillance systems in the future for real-time traffic monitoring, smart city framework, and integration of intelligent surveillance systems into emergency management systems.

To solve the persistently multiple object tracking in cluttered environments, this paper presents a novel tracking association approach based on the shortest path faster algorithm. First, the multiple object tracking is formulated as an integer programming problem of the flow network. Then we relax the integer programming to a standard linear programming problem. Therefore, the global optimum can be quickly obtained using the shortest path faster algorithm. The proposed method avoids the difficulties of integer programming, and it has a lower worst-case complexity than competing methods but better robustness and tracking accuracy in complex environments. Simulation results show that the proposed algorithm takes less time than other state-of-the-art methods and can operate in real time.

Persistently tracking multiple objects is very challenging when there exit occlusions. We present a tracking association approach based on the A ^* algorithm. We first formulate the multiple object tracking as an integer programming problem of the flow network. Under this framework, the integer assumption is relaxed to a standard linear programming problem. Therefore, the global optimal solution can quickly be obtained using the A ^* algorithm with dynamic weights. The proposed method avoids the difficulties of integer programming and more importantly, it has a lower worst-case complexity than competing methods but a better tracking accuracy and robustness in complex environments. Experiment results revealed that our proposed method achieved state-of-the-art time costs and can operate in real-time.