In recent years, the popularity of depth sensors and 3D scanners has led to a rapid development of 3D point clouds. Semantic segmentation of point cloud, as a key step in understanding 3D scenes, has attracted extensive attention of researchers. Recent advances in this topic are dominantly led by deep learning-based methods. In this paper, we provide a survey covering various aspects ranging from indirect segmentation to direct segmentation. Firstly, we review methods of indirect segmentation based on multi-views and voxel grids, as well as direct segmentation methods from different perspectives including point ordering, multi-scale, feature fusion and fusion of graph convolutional neural network (GCNN). Then, the common datasets for point cloud segmentation are exposed to help researchers choose which one is the most suitable for their tasks. Following that, we devote a part of the paper to analyze the quantitative results of these methods. Finally, the development trend of point cloud semantic segmentation technology is prospected.

Point cloud quality assessment (PCQA) aims to provide an objective and unified evaluation of the quality of the point cloud. Existing research in this field lacks a comprehensive exploration of cross-modal perceptual feature fusion, overlooking the intrinsic correlations and complementarities across different modalities. To establish explicit relationships between modal features and capture the importance differences across modalities, we propose a novel method based on the cross-modal deep-coupling framework (CMDC-PCQA) for evaluating objective indicators of point clouds. First, we divide the point cloud into patches of equal size and propose a point cloud feature extraction (SGSA) module based on point space and graph structure, which employs self-attention mechanism for fusion learning. Second, we capture the projected images of point clouds from multiple viewpoints. To improve the perception of 2-D texture and semantic features, we embed attention to spatial and channel information in the local acceptance domain of convolutional neural networks. Third, we propose a method called dual-stage feature attention interaction module (DFAM). It is designed to update the local and global weights of the semantic and geometric features that fully characterize deep coupling. The proposed method is validated on the SJTU-PCQA, WPC, and WPC2.0 databases. Experimental results demonstrate that our method has surpassed the state-of-the-art PCQA methods, which validate its effectiveness in the PCQA task.

Artificial intelligence technology in the context of smart manufacturing uses manufacturing data to enable the automatic detection, classification, and identification of products in the production process, reducing production costs and human consumption, thereby improving production efficiency and product quality. Federated learning enables the distributed implementation of AI technologies, keeping data local to avoid privacy leaks. However, data heterogeneity factors have an impact on federated learning in a manufacturing context, and this paper proposes a customer degree selection method based on model parameter variation. The method relies on transmitting the local model changes in the participants to reflect the data characteristics, calculates the model similarity of the participants using graph theory and similarity, and uses the Top-K mechanism to filter the original participant set through the similarity scores of graph nodes to reduce the influence of heterogeneity factors in the participant set and maximize the training effect and accuracy of federated learning. The effectiveness of this method was verified by using the Dirichlet distribution to perform non-IID data partitioning on the power system attack dataset and the hard disk fault detection dataset.