Guangshuai Liu

Accurate measurement and extraction of groove geometry under intense arc light and specular reflection is a critical challenge for adaptive pipeline welding. To address this issue, this paper proposes an integrated framework comprising robust visual perception and a data-driven process model.First, a high-precision multi-segment Random Sample Consensus (RANSAC) visual extraction algorithm combined with spatial Region of Interest (ROI) filtering is proposed. Compared with the traditional Douglas-Peucker algorithm, the proposed method significantly enhances measurement robustness against spatter noise. Experimental results indicate that the Root Mean Square Error (RMSE) of the root feature point in the depth direction is reduced from 2.184 mm to 1.584 mm. Second, utilizing these high-fidelity visual measurement data, a process prediction model based on Particle Swarm Optimization-Gaussian Process Regression (PSO-GPR) is established to address the complex non-linear mapping and small-sample limitations. The model achieves a determination coefficient (R2) of 0.9428 and an RMSE of 0.1321 in predicting weld cross-sectional features, outperforming traditional BP, RF, and SVR models while providing uncertainty Finally, an adaptive multi-pass welding path planning strategy is designed based on the predicted parameters. A six-layer filling experiment demonstrates that the average absolute path tracking error is constrained under 0.3 mm, achieving uniform weld formation without undercutting. This method provides a highly reliable visual measurement and control solution for intelligent large-scale pipeline construction.

Due to the shortage of rural labor and an increasingly aging population, promoting the mechanized plucking of bulk tea and improving plucking efficiency have become urgent problems for tea plantations. Previous bulk tea plucking machines have not fully adapted to tea plantations in hilly areas, necessitating enhancements in the performance of cutter profiling. In this paper, we present an automatic cutter profiling method based on an RGB-D camera, which utilizes the depth information of bulk tea shoots to tackle the issues mentioned above. Specifically, we use improved super-green features and the Otsu method to detect and segment the shoots from the RGB images of the tea canopy taken from different lighting conditions. Furthermore, the cutting pose based on the depth value of the tea shoots can be generated as a basis for cutter profiling. Lastly, the profiling task is completed by the upper computer controlling motors to adjust the cutter pose. Field tests were conducted in the tea plantation to verify the proposed profiling method’s effectiveness. The average bud and leaf integrity rate, leakage rate, loss rate, tea making rate, and qualified rate were 81.2%, 0.91%, 0.66%, and 90.4%, respectively. The results show that the developed algorithm can improve cutting pose calculation accuracy and that the harvested bulk tea shoots meet the requirements of machine plucking quality standards and the subsequent processing process.

Evaluation of the deviation zone based on discrete measured points is crucial for quality control in manufacturing and metrology. However, deviation-zone evaluation is a highly nonlinear problem that is difficult to solve using traditional numerical optimization methods. Swarm intelligence has many advantages in solving this problem: it produces gradient-free, high-quality solutions and is characterized by its ease of implementation. Therefore, this study applies an improved Harris hawks algorithm (HHO) to tackle the problem. The average fitness is applied to replace the random operator in the exploration phase to solve the problem of conflicting exploration strategies due to randomness. In addition, the salp swarm algorithm (SSA) with a nonlinear inertia weight is embedded into the HHO, such that the superior explorative ability of SSA can fill the gap in the exploration of HHO. Finally, the optimal solution is greedily selected between SSA-based individuals and HHO-based individuals. The effectiveness of the proposed improved HHO optimizer is checked through a comparison with other swarm intelligence methods in typical benchmark problems. Moreover, the experimental results of form deviation-zone evaluation on primitive geometries show that the improved method can accurately solve various form deviations, providing an effective general solution for primitive geometries in the manufacturing and metrology fields.

This paper introduces a robust normal estimation method for point cloud data that can handle both smooth and sharp features. Our method is based on the inclusion of neighborhood recognition into the normal mollification process in the neighborhood of the current point: First, the point cloud surfaces are assigned normals via a normal estimator of robust location (NERL), which guarantees the reliability of the smooth region normals, and then a robust feature point recognition method is proposed to identify points around sharp features accurately. Furthermore, Gaussian maps and clustering are adopted for feature points to seek a rough isotropic neighborhood for the first-stage normal mollification. In order to further deal with non-uniform sampling or various complex scenes efficiently, the second-stage normal mollification based on residual is proposed. The proposed method was experimentally validated on synthetic and real-world datasets and compared to state-of-the-art methods.

This paper introduces a robust and accurate normal estimation method for 3D point clouds. Our proposed technique is also robust towards noise and is capable of preserving sharp features in the input model. Our method presupposes that the normal of a point can be constituted from at least one in the normal set from the planes in its neighborhood, and its core idea is based on a local plane voting strategy, where each vote takes the entropy value and plane credibility into consideration. In addition, the average fitting residuals and the plane density are designed to further effectively deal with noise and non-uniformly sampled point clouds. The validity and reliability of our approach are confirmed by contrast to the most relevant state-of-the-art methods and by comprehensive experiments on synthetic and real-world data.

As a kind of information-intensive 3D representation, point cloud rapidly develops in immersive applications, which has also sparked new attention in point cloud compression. The most popular dynamic methods ignore the characteristics of point clouds and use an exhaustive neighborhood search, which seriously impacts the encoder’s runtime. Therefore, we propose an improved compression means for dynamic point cloud based on curvature estimation and hierarchical strategy to meet the demands in real-world scenarios. This method includes initial segmentation derived from the similarity between normals, curvature-based hierarchical refining process for iterating, and image generation and video compression technology based on de-redundancy without performance loss. The curvature-based hierarchical refining module divides the voxel point cloud into high-curvature points and low-curvature points and optimizes the initial clusters hierarchically. The experimental results show that our method achieved improved compression performance and faster runtime than traditional video-based dynamic point cloud compression.