The processing of underwater images can vastly ease the difficulty of underwater robots’ tasks and promote ocean exploration development. This paper proposes a fast and efficient underwater image enhancement model based on conditional GAN with good generalization ability using aggregation strategies and concatenate operations to take full advantage of the limited hierarchical features. A sequential network can avoid frequently visiting additional nodes, which is beneficial for speeding up inference and reducing memory consumption. Through the structural re-parameterization approach, we design a dual residual block (DRB) and accordingly construct a hierarchical attention encoder (HAE), which can extract sufficient feature and texture information from different levels of an image, and with 11.52% promotion in GFLOPs. Extensive experiments were carried out on real and artificially synthesized benchmark underwater image datasets, and qualitative and quantitative comparisons with state-of-the-art methods were implemented. The results show that our model produces better images, and has good generalization ability and real-time performance, which is more conducive to the practical application of underwater robot tasks.

The process of microwave heating involves the coupling of multiple physical phenomena, specifically including the distribution of the electromagnetic field in the resonant cavity. The electromagnetic effect generates heat and encourages the transfer of heat inside the material. In this numerical study, a 3D computer model of microwave heating of Al₂O₃/SiC composites using a multimode microwave heating chamber was established based on the simulation software COMSOL Multiphysics 5.6, and the symmetry treatment of the model was carried out, which effectively reduced the amount of model calculations and accurately analyzed the microwave heating characteristics of the samples. The analysis of the microwave heating characteristics of the sample was mainly preformed from the perspective of the electric field distribution in the resonant cavity, the sample heating rate and the sample heating uniformity, and then it was determined how the microwave source power and sample mold selection affect the temperature and electric field parameters of the sample. After experimental verification, the error between the simulation results and the temperature parameters obtained from the actual experiments is less than 2%. This study contributes to further understanding the heating behavior of Al₂O₃/SiC composites in complex multimode microwave heating environments and can be used to control the dynamic parameters during microwave heating in order to improve the heating rate and heating uniformity of samples.

As a nonverbal cue, gaze plays a critical role in communication, expressing emotions and reflecting mental activity. It has widespread applications in various fields. Recently, the appearance-based gaze estimation method, which utilizes CNN (convolutional neural networks), has rapidly improved the accuracy and robustness of gaze estimation algorithms. Due to their insufficient ability to capture global relationships, the present accuracy of gaze estimation methods in unconstrained environments, has the potential for improvement. To address this challenge, the focus of this paper is to enhance the accuracy of gaze estimation, which is typically measured by mean angular error. In light of Transformer’s breakthrough in image classification and target detection tasks, and the need for an efficient network, the Transformer-enhanced-CNN method is a suitable choice. This paper proposed a novel model for 3D gaze estimation in unconstrained environments, based on the Bottleneck Transformer block and multi-loss methods. Our designed network (BoT2L-Net), incorporates self-attention through the BoT block, utilizing two identical loss functions to predict the two gaze angles. Additionally, the back-propagation network was combined with classification and regression losses, to improve the network’s accuracy and robustness. Our model was evaluated on two commonly used gaze datasets: Gaze360 and MPIIGaze, achieving mean angular errors of 11.53° and 9.59° for front 180° and front-facing gaze angles, respectively, on the Gaze360 testing set, and a mean angular error of 3.97° on the MPIIGaze testing set, outperforming the CNN-based gaze estimation method. The BoT2L-Net model proposed in this paper performs well on two publicly available datasets, demonstrating the effectiveness of our approach.