Point Cloud Data Classification and Segmentation Method Based on Salient Point Sampling

Abstract

The invention discloses a point cloud data classification and segmentation method based on salient point sampling, and proposes a point cloud data classification and segmentation network based on salient point sampling. The two network backbones are composed of a new salient point sampling algorithm (SPS) and multiple Both SPS and MS‑LSFE can be flexibly inserted into other networks to assist sampling or feature extraction. For the convenience of calling, this method encapsulates SPS and MS‑LSFE to form a multi-scale salient feature extraction module (MS‑SFE), which achieves a balance between performance and parameter quantity. The present invention carries out the classification test on the standard public data set ModelNet40, ensuring that the number of parameters is only 0.3×10 6 The classification accuracy reached 92.42% at the same time; the segmentation experiments were carried out on the standard public datasets ShapeNet, S3DIS and Semantic3D, and the segmentation accuracy could reach 85.1%, 61.8%, and 65.8%, respectively. The above classification and segmentation results are at the leading or comparable level in similar work, which verifies the feasibility and effectiveness of this method.

Description

technical field [0001] The invention relates to the technical fields of computer graphics, computer vision and intelligent recognition, in particular to a point cloud data classification and segmentation method based on salient point sampling. Background technique [0002] With the popularity of 3D point cloud acquisition equipment such as lidar and stereo cameras, and the development of related fields such as autonomous robots and autonomous driving, there is an increasing demand for direct processing of point clouds in order to avoid costly mesh reconstruction. As a result, large-scale repositories of 3D point clouds are beginning to emerge, and convolutional neural networks (CNNs) are becoming one of the most important techniques to greatly improve point cloud processing capabilities. [0003] The application scenarios of the point cloud model, such as unmanned driving, mostly require real-time acquisition of point cloud data to complete the preliminary segmentation and i...

AI Technical Summary

Problems solved by technology

[0006] Qi et al. (C.R.Qi, H.Su, K.Mo, and L.J. Guibas. Pointnet: deep learning on pointsets for 3d classification and segmentation[C] / / Proceedings of the IEEEConference on Computer Vision and Pattern Recognition, pages 652–660, 2017.) The PointNet network proposed for the characteristics of point cloud data first applies deep learning to point cloud classification tasks. PointNet uses T-Net to achieve effective alignment of data and features, and uses Maxpooling symmetric function to extract order-independent global features. ModelNet40 A classification accuracy of 89.20% has been achieved on the above. However, PointNet cannot extract the local features of point cloud data, and a series of work has been designed on how to effectively extract the local features of point cloud data.

Images