Point cloud local feature extraction method and device, equipment and storage medium

Abstract

The invention discloses a point cloud local feature extraction method, device and equipment and a storage medium. The method comprises the following steps: firstly, providing a new graph attention network for point cloud local feature extraction, and enabling the network to rapidly and accurately carry out the semantic segmentation of a three-dimensional point cloud; secondly, constructing a local expansion graph area of each point by using an expanded K nearest neighbor search algorithm, and performing local feature expression by using Euclidean distance geometric correlation between a central point and a neighborhood thereof; finally, applying an attention mechanism to a designed network layer, called as a graph attention layer, dynamically learning the context attention features on the local expansion graph by giving proper weights to adjacent edges of a central point, and better reserving local geometric details of the point cloud through attention pooling operation. Compared with an existing point cloud local feature extraction method, the method achieves better performance in three-dimensional point cloud shape classification and segmentation tasks.

Description

technical field [0001] The present invention relates to the field of three-dimensional point cloud processing, and more specifically, relates to a point cloud local feature extraction method, device, equipment and storage medium. Background technique [0002] Point clouds provide simple and intuitive geometric representations for 3D objects, and are increasingly used in many practical applications such as autonomous driving, indoor navigation, and robotics. Therefore, the analysis and processing of point clouds has attracted more and more attention from researchers, especially in recent years, methods based on deep learning have shown extraordinary performance in point cloud feature extraction. However, unlike regular pixels in a 2D image, a 3D point cloud is composed of a series of unorganized points in a non-Euclidean space, and typical 2D convolutions cannot directly analyze 3D data due to its irregular and sparse structure. point cloud calculations. Researching an effe...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem that the traditional method cannot use long-distance geometric information for local fine feature extraction, the present invention constructs a point cloud local feature extraction network based on the expansion graph neural network. Aggregation to learn local features on dilated graphs and obtain enough local details

Images