Point cloud data processing method, neural network training method and related equipment

A technology of point cloud data and processing methods, applied in biological neural network models, special data processing applications, still image data retrieval, etc., can solve problems such as consuming large computer resources, and achieve the effect of improving implementation flexibility

Pending Publication Date: 2022-03-04
HUAWEI TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, since the entire point cloud needs to be sampled to determine the key points of the target, when the number of point clouds is large, the processing of the entire point cloud data will consume a lot of computer resources.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Point cloud data processing method, neural network training method and related equipment
  • Point cloud data processing method, neural network training method and related equipment
  • Point cloud data processing method, neural network training method and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] Books and the like, the term above figures present specification and claims, "first", "second" are used for distinguishing between similar objects, and not necessarily for describing a particular sequential or priorities. It should be understood that such terms may be used interchangeable under appropriate circumstances, this is merely to distinguish embodiment described embodiments of the present application, the object of the same attributes used in the description. Furthermore, the terms "including" and "having," as well as any of their deformation, intended to cover non-exclusive inclusion, so as to contain a series of unit process, method, system, or apparatus not necessarily limited to those elements, but may include no clear or to such process, method, article, or apparatus other inherent to the units listed.

[0078] Below in conjunction with the accompanying drawings, of embodiments of the present application will be described. Apparent to those of ordinary skill i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention discloses a point cloud data processing method, a neural network training method and related equipment. The method can be used in the field of point cloud data processing in the field of artificial intelligence. The method comprises the following steps: acquiring point cloud data corresponding to a target environment, wherein the point cloud data is divided into a plurality of target cubes; generating an initial feature of each target cube according to the initial information of the target point in each target cube; updating the initial features of the plurality of target cubes according to an attention mechanism to obtain updated features of the plurality of target cubes; and performing feature processing operation on the updated features of the plurality of target cubes to obtain a prediction result corresponding to the point cloud data. Therefore, computer resources consumed in the whole point cloud data processing process are reduced, important information carried by the point cloud data can be focused, and the accuracy of the output prediction result is improved.

Description

Technical field [0001] The present application relates to the field of artificial intelligence, in particular to a method for processing point cloud data, the neural network training method and associated apparatus. Background technique [0002] Artificial Intelligence (AI) is the use of digital computers or digital computer-controlled machine simulations, extensions, and extensions of the intelligence, perceived environment, access to knowledge, and use knowledge to achieve best results, methods, techniques, and application systems. In other words, artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence, and produce a new kind of intelligent machines capable to respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, making the machine with perception, reasoning and decision-making. [0003] Using the model point clo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06V40/16G06V20/64G06N3/02G06K9/62G06F16/51G06V10/774
CPCG06F16/51G06N3/02G06F18/214
Inventor 钮敏哲徐航许春景
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap