Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Point cloud data screening method and device, electronic equipment and storage medium

A point cloud data and screening method technology, applied in the computer field, can solve the problems of too little point cloud data, too much point cloud data, and the inability to realize fast display, etc., and achieve the effect of avoiding shape distortion

Pending Publication Date: 2021-10-12
BEIJING JINGDONG 360 DEGREE E COMMERCE CO LTD
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] There is no certain standard for the thinning algorithm of point cloud data, and it is often neglected. In order to quickly load and display point cloud data, if the thinning rate is too high, the data will be seriously distorted, and the obtained results cannot meet the requirements of each algorithm module of automatic driving; If the thinning rate is too small, the purpose of fast display cannot be achieved
For the display method based on grid division, for irregular and complex features, violent grid division will lead to too much point cloud data in some grids, and too little point cloud data or no point cloud in some grids data, so the displayed results do not correctly reflect the organization of the point cloud

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 screening method and device, electronic equipment and storage medium
  • Point cloud data screening method and device, electronic equipment and storage medium
  • Point cloud data screening method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] figure 1 It is a flow chart of a point cloud data screening method provided by Embodiment 1 of the present invention. This embodiment is applicable to sampling the original point cloud of an object (for example, a large number of point clouds obtained through vehicle-mounted radar scanning), so as to achieve the original The scene where the point cloud is thinned out. The method can be executed by a device for screening point cloud data, and the device can be implemented by means of software and / or hardware.

[0029] Such as figure 1 As shown, the method specifically includes the following steps:

[0030] Step 110, perform grid division on the original point cloud, and obtain octree structure data corresponding to the original point cloud.

[0031] Wherein, the original point cloud usually refers to the point cloud obtained by scanning by the vehicle radar. Because the point cloud obtained by vehicle-mounted radar scanning has rich details, complex structure, and hu...

Embodiment 2

[0049] image 3 It is a flow chart of a method for screening point cloud data provided by Embodiment 2 of the present invention. On the basis of the above embodiments, this embodiment, for step 120 "respectively select the leaf nodes of each level in the octree structure data Sampling the point cloud to get the target point cloud" is described in detail. The explanations of terms that are the same as or corresponding to those in the foregoing embodiments are not repeated here.

[0050] see image 3 The point cloud data screening method provided in this embodiment specifically includes the following steps:

[0051] Step 310, perform grid division on the original point cloud, and obtain octree structure data corresponding to the original point cloud.

[0052] Step 320 , for each level node in the octree structure data, sample the leaf nodes of the current level according to the set sampling rate, and store the sampled target point cloud in the directory of the current level. ...

Embodiment 3

[0072] Figure 4 It is a flow chart of a point cloud data screening method provided by Embodiment 3 of the present invention. On the basis of the above embodiments, this embodiment applies the high-resolution target point cloud of the original point cloud to the automatic driving simulation platform. In order to enable the automatic driving simulation platform to realize the purpose of fast and smooth display of point clouds, so as to meet the real-time requirements of automatic driving. The explanations of terms that are the same as or corresponding to those in the foregoing embodiments are not repeated here.

[0073] Such as Figure 4 As shown, the method includes the following steps:

[0074]Step 410: Carry out grid division on the original point cloud, obtain the octree structure data corresponding to the original point cloud, and establish the data index structure of the octree structure data at the same time.

[0075] Step 420: Sampling the point clouds in the leaf no...

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 screening method and device, equipment and a storage medium. The method comprises the steps: carrying out grid subdivision on an original point cloud, and obtaining the octree structure data corresponding to the original point cloud; and sampling point clouds in leaf nodes of each level in the octree structure data to obtain target point clouds. Through the technical scheme of the embodiment of the invention, the purposes of sampling the original point cloud data and obtaining the high-resolution point cloud data representing the detail features of the object are achieved.

Description

technical field [0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a point cloud data screening method, device, electronic equipment and storage medium. Background technique [0002] The loading and display of point cloud data is an important part of the autonomous driving simulation platform. Because the point cloud data collected by vehicle radar has rich details, complex structure and large data volume, loading and displaying at one time not only has certain requirements for storage space, but also has certain requirements for hardware devices, such as memory, CPU (Central ProcessorUnit, central processing unit), graphics card, etc. Therefore, the fast and smooth display of point cloud data in the automatic driving simulation platform is one of the main indicators to measure the automatic driving simulation platform. [0003] At present, there are two commonly used point cloud data display methods: one is to ...

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): G06T17/00G06T7/149G06T3/40
CPCG06T17/005G06T7/149G06T3/4053G06T2207/10028
Inventor 王帅
Owner BEIJING JINGDONG 360 DEGREE E COMMERCE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com