Point cloud data processing method and device and electronic equipment

Abstract

The invention provides a point cloud data processing method and device and electronic equipment, and relates to the technical field of data processing, and the method comprises the steps: obtaining anoriginal point cloud data set, extracting the feature information of each point in the point cloud data set, and carrying out the sampling processing of the original point cloud data set, so as to generate a key point set of the original point cloud data set; for each key point in the key point set, calculating Gaussian distances from all points in the original point cloud data set to the key point according to the feature information; determining an adjacent point set of the key point based on the Gaussian distance; performing feature aggregation on the adjacent point sets to generate feature points corresponding to the key points; and counting the feature points corresponding to each key point, and generating a feature point set of the original point cloud data set. According to the point cloud data processing method and device and the electronic equipment provided by the invention, the manual intervention process is reduced, so that the possibility of wrong feature extraction can be reduced, the feature robustness is enhanced, and the final perception performance is improved.

Description

technical field [0001] The technical field of data processing of the present invention, in particular, relates to a point cloud data processing method, device and electronic equipment. Background technique [0002] With the rapid development and cost reduction of 3D sensor technology (lidar, RGB-D camera, multi-eye camera, etc.), more and more autonomous driving devices begin to use 3D sensors as necessary perception sensors. Compared with traditional 2D sensors (such as color cameras), 3D sensors can obtain rich geometric position information in the traffic environment, improve the perception performance of unmanned vehicles, and thus ensure the safety and efficiency of autonomous driving equipment. [0003] Usually, when a 3D sensor detects a target, it obtains 3D point cloud data. Due to the characteristics of point cloud data such as sparsity, disorder, and rotation invariance, the current perception method based on point cloud data mainly Convert point cloud data into ...

AI Technical Summary

Problems solved by technology

In the process of structuring the point cloud, this kind of method will inevitably cause the loss of the original point cloud information, and the use of the 2D convolution method on the 3D data will also cause the extracted features to be not robust enough, and the existing The convolution method in the technology requires more manual intervention, and it is difficult to guarantee the accuracy and universal applicability of the calculation, thus affecting the final perception performance

Images