No abstract

Local information coding helps capture the fine-grained features of the point cloud. The point cloud coding mechanism should be applicable to the point cloud data in different formats. However, the local features of the point cloud are directly affected by the attributes, size and scale of the object. This paper proposes an Adaptive Locally-Coded point cloud classification and segmentation Network coupled with Genetic Algorithm(ALCN-GA), which can automatically adjust the size of search cube to complete network training. ALCN-GA can adapt to the features of 3D data at different points, whose adjustment mechanism is realized by designing a robust crossover and mutation strategy. The proposed method is tested on the ModelNet40 dataset and S3DIS dataset. Respectively, the overall accuracy and average accuracy is 89.5% and 86.5% in classification, and overall accuracy and mIoU of segmentation is 80.34% and 51.05%. Compared with PointNet, average accuracy in classification and mIoU of segmentation is improved about 10% and 11% severally.

Bonding the ceramic green-bodies of the seat ring to the cup body is an important step in the production process of the toilet. This paper proposes a pose transformation estimation method based on feature extraction and matching in ceramic green body bonding process. This method uses a Local Feature Statistics Histogram (LFSH) to extract the features of the bonding surfaces and find the corresponding point sets. Then, a Sample Consensus Initial Aligment (SAC-IA) algorithm combined with LFSH features is used to perform coarse registration calculation. Finally, using the Iterative Cloest Point (ICP) algorithm, the result of the coarse registration is used as the initial value to complete the fine registration and obtain the pose transformation matrix. Before registration, the relative poses of the two point clouds are randomly transformed. This method is tested on the point cloud data of the cup body and the seat ring. Experimental results show that the role of SAC-IA can increase the speed of registration compared to using ICP alone.

No abstract