Three-dimensional point cloud processing method, device and equipment

Abstract

The invention provides a three-dimensional point cloud processing method, device and equipment. The method comprises the following steps: acquiring point cloud data comprising a plurality of points; inputting the point cloud data into a pre-trained convolutional neural network; the convolutional neural network comprises a convolution module for geometric feature information sharing; for each pointin the point cloud data, obtaining a neighbor point of the point in the Euclidean space based on the convolution module, and determining a neighbor point of the point in the feature value space basedon the neighbor point of the point in the Euclidean space; aggregating the neighbor points of the points in the Euclidean space and the neighbor points of the points in the feature value space to obtain aggregated features; and performing feature learning on the aggregated features by using a multi-layer perceptron, and performing maximum pooling operation on the dimensions of the neighbor pointsto obtain output features. A convolution structure is directly constructed to process three-dimensional point cloud data, so that the problems of data missing and data redundancy are effectively relieved.

Description

technical field [0001] The invention relates to the field of three-dimensional data processing, in particular to a processing method, device and equipment for a three-dimensional point cloud. Background technique [0002] Point cloud (full name in English is Point Cloud) is a collection of point data on the product appearance surface obtained by measuring instruments in reverse engineering. In addition to geometric positions, point cloud data also has color information. The color information is usually obtained through the camera to obtain the color image, and then the color information (RGB) of the pixel at the corresponding position is assigned to the corresponding point in the point cloud. The acquisition of intensity information is the echo intensity collected by the receiving device of the laser scanner. This intensity information is related to the surface material, roughness, incident angle and direction of the target, as well as the emission energy of the instrument a...

AI Technical Summary

Problems solved by technology

[0003] However, when processing point cloud data, because 3D point cloud data is different from images, 3D point cloud data is non-normalized, multi-view projection technology projects the non-normalized 3D point cloud into a 2D image, and then 2D Image processing. At present, the point cloud data needs to be converted into other data formats, such as projecting the 3D point cloud to a 2D image, as the input of the convolutional neural network; but this process has the following disadvantages: (1) Due to occlusion, the projection process itself will cause some data loss

(2) The calculation amount of the data conversion process is relatively large;

[0005] The voxel representation will cause data redundancy, which will cause a large memory footprint and consume more computer resources, and it is easy to lose the geometric information of spatial local details.

Images