Data processing method, apparatus and device, and readable storage medium

Abstract

The invention discloses a data processing method, apparatus and device, and a readable storage medium The data processing method comprises the following steps: acquiring a first aerial view; according to a preset random walk length, performing random walk processing on each initial cluster to obtain a point sequence set of each initial cluster; according to a preset proximity value algorithm, obtaining a target point sequence of each point sequence set, wherein the proximity value corresponding to the target point sequence is minimum; determining a vector representation form of each node and each edge in the target point sequence of each initial cluster, and obtaining first vector information of the nodes and second vector information of the edges, so as to enable a target neural network to obtain feature data in the first aerial view. According to the embodiment of the invention, the disorder of information between different dimensions in point cloud data can be reduced, so that the efficiency of deep learning of the point cloud data by a convolutional neural network is improved.

Description

technical field [0001] The present application belongs to the field of data processing, and in particular relates to a data processing method, device, equipment and readable storage medium. Background technique [0002] At present, with the rapid development of convolutional neural network, in the fields of computer vision and natural language processing, effective deep learning can be carried out based on convolutional neural network, such as image, audio and other data. [0003] Point cloud data points can include a wealth of information, such as three-dimensional coordinates (X, Y, Z), color, classification value, intensity value, time, etc. Due to the randomness and disorder of these information, it is usually impossible to use fixed Or a convolution kernel with a non-fixed size performs convolution operations on point cloud data. Therefore, when learning a convolutional neural network, the learning takes a long time and the learning effect is poor. Therefore, a kind of ...

AI Technical Summary

Problems solved by technology

[0003] Point cloud data points can include a wealth of information, such as three-dimensional coordinates (X, Y, Z), color, classification value, intensity value, time, etc. Due to the randomness and disorder of these information, it is usually impossible to use fixed Or a convolution kernel with a non-fixed size performs convolution operations on point cloud data. Therefore, when learning a convolutional neural network, the learning takes a long time and the learning effect is poor. Therefore, a kind of point cloud data is required for effective processing. To improve the efficiency of convolutional neural network for deep learning of point cloud data

Images