Surface reconfiguration softwares have many problems such as complicated operation on point cloud data, too many interaction definitions, and too stringent requirements for inputing data. Thus, it has not been widely popularized so far. This paper selects the unique Huizhou Architecture chuandou wooden beam framework as the research object, and presents a complete set of implementation in data acquisition from point, point cloud preprocessing and finally implemented surface reconstruction. Firstly, preprocessing the acquired point cloud data, including segmentation and filtering. Secondly, the surface's normals are deduced directly from the point cloud dataset. Finally, the surface reconstruction is studied by using Greedy Projection Triangulation Algorithm. Comparing the reconstructed model with the three-dimensional surface reconstruction softwares, the results show that the proposed scheme is more smooth, time efficient and portable.
Considering the influence of various factors, such as speed, angle, depth of water, weight, and water flow, on the underwater rescue robot, a method based on neural network is proposed. According to the characteristics of Elman and Jordan neural network, a new dynamic neural network is constructed. The network can be used to remember the state of the hidden layer and increase the feedback of the output node. The improved Jordan network is optimized by chaos particle swarm optimization algorithm. The optimized neural network is applied to identify the dynamic model of the underwater rescue robot. The simulation results show that the neural network has good convergence speed and accuracy.
1 January 2026 in Computer Science and Information Systems
Quality inspection of steel plate welding is critical in industrial manufacturing. However, weld proximity defects often present diverse morphologies, overlapping regions, and dense distributions, posing challenges to accurate industrial defect inspection. Therefore, we propose an industrial detector based on the EP-YOLOv7. First, an Efficient Multiscale Channel Attention (EMCA) is introduced to strengthen multi-scale feature perception and improve the model’s focus on weld proximity defects. Second, the EMCA module is integrated into the Efficient Layer Aggregation Network to enhance feature fusion and defect representation. Finally, a Partial-Bottleneck Decoupling Predictor Head (P-BD Head) is designed to significantly improve localization accuracy and reduce missed detections of small targets. Experimental evaluations on both a self-built weld proximity defect dataset and a public generalization dataset show that EP-YOLOv7 achieves mAP of 85.2%/56.2% and F1 scores of 80.3%/43.3%. Meanwhile, the model size increases by only 0.6 MB (total 37.9 MB), demonstrating that the proposed approach delivers substantial accuracy gains while maintaining lightweight computational complexity, suitable for practical industrial applications.