Point cloud semantic segmentation method and device and electronic equipment

Abstract

The invention provides a point cloud semantic segmentation method and device and electronic equipment, and relates to the field of artificial intelligence. The method comprises the steps of obtainingoriginal point cloud, and encoding point cloud data corresponding to the original point cloud through an encoding network model to obtain point cloud encoding features; inputting the point cloud coding characteristics into a decoding network model; obtaining an edge feature corresponding to the original point cloud according to the point cloud coding feature through an edge module branch in the decoding network model, and obtaining a point feature corresponding to the original point cloud according to the point cloud coding feature and the edge feature through a point module branch in the decoding network model; and performing classification prediction according to the point features and the edge features to obtain classification information corresponding to each point in the original point cloud. According to the point cloud semantic segmentation method and device, the information transmission range can be enlarged through point-edge mutual communication cooperation, local environmentinformation is better utilized, and the accuracy and efficiency of point cloud semantic segmentation are improved.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, in particular, to a point cloud semantic segmentation method, a point cloud semantic segmentation device, and electronic equipment. Background technique [0002] With the development of computer technology, computer vision and machine learning researchers are becoming more and more interested in image semantic segmentation. More and more application scenarios require accurate and efficient segmentation technology, such as automatic driving, indoor navigation, and even virtual reality. with augmented reality and more. [0003] At present, the technical solutions for segmenting 3D application scenarios based on deep learning mainly include voxel-based solutions and point cloud-based solutions. Issues such as low utilization; due to the irregularity and disorder of point clouds, the convolutional layers used to extract local regions cannot be applied to point clouds. [00...

AI Technical Summary

Problems solved by technology

[0003] At present, the technical solutions for segmenting 3D application scenarios based on deep learning mainly include voxel-based solutions and point cloud-based solutions. Issues such as low utilization; due to the irregularity and disorder of point clouds, the convolutional layer used to extract local regions cannot be applied to point clouds

Images