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

Laser point cloud data set augmentation method and device, and readable storage medium

A technology of laser point cloud data and laser point cloud, which is applied in the field of data processing, can solve the problems of low efficiency of laser point cloud labeling, achieve the effects of reducing the degree of manual participation, efficient acquisition, and low efficiency

Pending Publication Date: 2018-11-06
SHENZHEN ECHIEV AUTONOMOUS DRIVING TECH CO LTD
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to provide a laser point cloud data set augmentation method, device and readable storage medium, aiming to solve the problem of low efficiency of laser point cloud labeling caused by manual labeling of laser 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
  • Laser point cloud data set augmentation method and device, and readable storage medium
  • Laser point cloud data set augmentation method and device, and readable storage medium
  • Laser point cloud data set augmentation method and device, and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0066] Please refer to figure 2 , figure 2 For the first embodiment of the laser point cloud data set augmentation method of the present invention, the method includes the following steps:

[0067] Step S10, acquiring a laser point cloud target data set; wherein, the laser point cloud target data set includes marked laser point cloud data;

[0068] The laser point cloud target data set is a collection of laser point cloud data obtained after detection by laser radar, which includes several laser point cloud data that have been marked. The marked laser point cloud data specifically refers to several laser point cloud data marked in the laser point cloud target data set; for example, for image 3 The contour of a certain car in the real road image is marked to define the outer contour of the car. The point cloud data corresponding to the marked points of the car outline (not marked in the figure) is the marked laser point cloud data.

[0069] It should be noted that the "l...

specific Embodiment approach 1

[0080] Obtain preset rotation parameters; rotate the selected laser point cloud data according to the preset rotation parameters, so as to transform the coordinates of the laser point cloud data.

[0081] The preset rotation parameters specifically include the position of the rotation axis (or rotation point), the rotation direction and the rotation angle. It should be noted that the rotation here refers to the rotation of the laser point cloud data of each object around different rotation axes, that is, the relative position of each object and its laser point cloud data changes after the rotation is performed. Wherein, the rotation axis adopted when the laser point cloud data of the object is rotated is preferably a normal line passing through the center of gravity of the object and perpendicular to the plane where the object is located. For example, Figure 4 for right image 3 The schematic diagrams of the new bounding boxes Z1-1 and Z2-1 are obtained after the laser poin...

specific Embodiment approach 2

[0082] Obtain preset stretching parameters; perform stretching transformation on the selected laser point cloud data according to the preset stretching parameters, so as to transform the coordinates of the laser point cloud data.

[0083] The preset stretching parameters specifically include the position of the stretching base point, the stretching direction, and the stretching distance. For example, if Figure 5 as shown, image 3 After stretching and transforming the original bounding boxes Z1 and Z2 in Figure 5 The length, width and height of the 3D bounding box of the vehicle in the vehicle may change to form new 3D bounding boxes Z1-2, Z2-2; at the same time, the coordinates of the marked laser point cloud data in the 3D bounding box will also change with the The change forms a new labeled laser point cloud data.

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 invention provides a laser point cloud data set augmentation method. The method comprises the steps of: acquiring a laser point cloud target data set; wherein the laser point cloud target data setcomprises labeled laser point cloud data; selecting laser point cloud data to be processed in the target data set; processing the selected laser point cloud data based on a preset data processing manner; and acquiring the processed laser point cloud data to generate a corresponding laser point cloud augmentation data set. The invention also provides a laser point cloud data set augmentation device and a readable storage medium. The invention solves the problem that the existing laser point cloud manual labeling method leads to low efficiency of laser point cloud labeling.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a laser point cloud data set augmentation method, device and readable storage medium. Background technique [0002] At present, lidar has become the core detection sensor used in the field of unmanned driving. The basic working principle of lidar is that lidar emits laser light and receives the reflected laser light after it hits the surface of the object. The reflected laser will carry information such as the orientation and distance of the object, so the laser radar can determine the orientation, distance, shape and other information of the object according to the received reflected laser, so as to perform three-dimensional detection of the object. [0003] Lidar will generate a large amount of scanning point data during the detection process (especially in the field of unmanned driving), and such scanning point data is generally called 3D laser point cloud data. 3D l...

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): G06T19/20G01S7/48G01S17/93
CPCG06T19/20G01S7/4802G06T2219/2016G01S17/931Y02A90/10
Inventor 刘新宋朝忠陈潇李逸岳
Owner SHENZHEN ECHIEV AUTONOMOUS DRIVING TECH CO LTD
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com