Lihua Zhang

Underwater vision technology serves as the core foundation for enabling “perception and interaction” in intelligent underwater robotic systems; however, its performance is severely constrained by image degradation. This paper provides a narrative review of research achievements in the field of underwater vision over the past decade, covering research approaches in mechanisms, methods, data, and applications. First, we analyze the physical models of underwater image degradation and elucidate its causes. Building on this foundation, the paper focuses on reviewing the algorithmic contributions of artificial intelligence to underwater image enhancement and restoration, summarizing multiple mainstream datasets such as UIEB and EUVP, as well as image quality evaluation metrics. Furthermore, through multi-benchmark experiments, we compare representative methods in terms of image quality, robustness to degradation, computational efficiency, and downstream visual tasks. The experimental results indicate that the performance of different methods varies depending on the dataset, evaluation metrics, and degradation conditions, and that the performance rankings differ across various evaluation metrics. Finally, this paper discusses key challenges, such as the discrepancy between objective evaluation and subjective perception, as well as model robustness and environmental adaptability, and proposes future research directions to provide guidance for the development of underwater image enhancement and restoration technologies and task-oriented evaluation.

Underwater quadrotor vehicles operating in complex nearshore environments face challenges in three-dimensional path planning, obstacle-triggered replanning, and trajectory tracking under external disturbances. To address these issues, this paper evaluates an enhanced rapidly exploring random tree (iRRT) planner and a model predictive control–proportional–integral–derivative (MPC–PID) tracking strategy with residual disturbance estimation. The planner combines guided sampling, environment-aware adaptive extension, collision-checked reverse greedy pruning, and cubic B-spline smoothing. A bisection-based handoff reconnects the remaining safe path after a newly introduced obstacle; post-solution informed sampling is examined separately as an ablation. The tracking controller is evaluated on a nonlinear six-degree-of-freedom vehicle model under a seeded, wave-shaped disturbance proxy. In 30 runs on the original voxel map, both RRT and iRRT produced safe paths in the static and fixed-obstacle replanning cases under the same additional radius-two voxel-neighborhood test. Relative to RRT, iRRT reduced the mean number of raw path nodes by 37.4% in the static case and 12.8% after replanning, whereas its small mean path-length differences were not conclusive. Under matched paths and disturbance phases, adding residual estimation to MPC–PID reduced mean position RMSE by 12.1% on the static path and 9.7% on the replanned path. Component ablations and additional synthetic maps further examine the contributions and limits of the planning modules. These results support the proposed integration under the stated numerical assumptions; measured hydrodynamics and vehicle experiments remain to be investigated.

Industrial-grade printed circuit boards (PCBs) exhibit high structural order and inherent geometric symmetry, where minute surface defects essentially constitute symmetry-breaking anomalies that disrupt topological integrity. Detecting these anomalies is quite challenging due to issues like scale variation and low contrast. Therefore, this paper proposes a symmetry-aware object detection framework, DAS-YOLO, based on an improved YOLOv11. The U-shaped adaptive feature extraction module (Def-UAD) reconstructs the C3K2 unit, overcoming the geometric limitations of standard convolutions through a deformation adaptation mechanism. This significantly enhances feature extraction capabilities for irregular defect topologies. A semantic-aware module (SADRM) is introduced at the backbone and neck regions. The lightweight and efficient ESSAttn improves the distinguishability of small or weak targets. At the same time, to address information asymmetry between deep and shallow features, an iterative attention feature fusion module (IAFF) is designed. By dynamically weighting and calibrating feature biases, it achieves structured coordination and balanced multi-scale representation. To evaluate the validity of the proposed method, we carried out comprehensive experiments using publicly accessible datasets focused on PCB defects. The results show that the Recall, mAP@50, and mAP@50-95 of DAS-YOLO reached 82.60%, 89.50%, and 46.60%, respectively, which are 3.7%, 1.8%, and 2.9% higher than those of the baseline model, YOLOv11n. Comparisons with mainstream detectors such as GD-YOLO and SRN further demonstrate a significant advantage in detection accuracy. These results confirm that the proposed framework offers a solution that strikes a balance between accuracy and practicality in addressing the key challenges in PCB surface defect detection.

Common PCB (Printed Circuit Board) defects include missing holes, shorts, spurs, etc., which may lead to product performance degradation, malfunction or safety hazards. Within the framework of Smart Manufacturing and Industry 4.0, industry strives to achieve automated and intelligent PCB defect inspection by using advanced machine vision systems and artificial intelligence algorithms. However, PCB defect detection faces challenges such as high density and miniaturization, complex background interference, and multiscale targets. For this reason, this paper proposes a new method for PCB defect detection according to a hierarchical scale-aware attention (HSA) mechanism based on RT-DETR (Real-Time Detection Transformer), and thus the method is coded as HSA-RTDETR. The core of the new method resides in the enhancement of feature information of small target defects in a feature fusion network. Firstly, a new backbone network, R18-Faster-EMA, is designed to make the overall model more efficient; Secondly, the AIFI (Attention-based Intra-scale Feature Interaction) module is redesigned to replace the original multihead self-attention mechanism with cascaded group attention to highlight important features. Thirdly, a hierarchical scale-aware pyramid attention network (HS-PAN) is designed to realize multi-scale feature fusion and learn more comprehensive feature arrays. Finally, to improve the efficiency of the model, a new loss function is designed to speed up convergence and prioritize small target defects. Experiments show that the HSA-RTDETR method achieves a mean average precision of 96.9% for six defects in a PCB dataset, which outperforms other existing models in terms of precision and recall. Compared with the original RT-DETR algorithm, the proposed method improves precision, recall, and mAP50 by 5.8%, 7.9% and 5.4%, respectively, In addition, the inference speed reaches 66.2 frames per second (FPS), which is deemed effective for the detection of small target defects in PCBs.

(K_0.5Na_0.5)1–3xEu_xNbO₃ (0≤x≤0.05) lead-free ceramics have been prepared by a conventional solid state reaction. XRD show that the ceramics possess a pure perovskite structure with orthorhombic symmetry. Dopant Eu restrains the grain growth, decreases the ferroelectric-paraelectric phase transition temperature and leads to a diffuse phase transition. With the increase of Eu, the observed remanent polarization (P_r) decreases while the coercive field (E_c) remains almost unchanged. Nevertheless, for the increase in relative permittivity, the sample with x = 0.005 exhibits the optimum piezoelectric properties, giving a large piezoelectric coefficient (d₃₃ = 121 pC/N) and a high planar electromechanical coupling coefficient (k_p = 0.41).