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

Point cloud data denoising method and device, equipment and storage medium

A technology of point cloud data and cloud data, which is applied in image data processing, character and pattern recognition, instruments, etc. It can solve the problem of large amount of denoising operations in the whole frame, high delay in the obstacle perception process, and difficulty in accurately removing floating point cloud data. Noise and secondary reflection noise, etc., to achieve the effect of improving accuracy and efficiency, improving accuracy and real-time performance

Pending Publication Date: 2020-07-10
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the full frame denoising method of the existing technology is difficult to accurately remove floating noise and secondary reflection noise in the point cloud data, and the calculation of the whole frame denoising is relatively large, resulting in a high delay in the obstacle perception process

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 denoising method and device, equipment and storage medium
  • Point cloud data denoising method and device, equipment and storage medium
  • Point cloud data denoising method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0059] figure 1 It is a flow chart of a point cloud data denoising method according to the first embodiment of the present application. This embodiment is applicable to the case of denoising point cloud data, especially for removing floating noise and secondary reflection noise. The method can be performed by a point cloud data denoising device, which is implemented in the form of software and / or hardware, and can be preferably configured in a radar-carrying device, for example, a self-driving vehicle equipped with a radar, or a mobile robot, etc. . Such as figure 1 As shown, the method specifically includes the following steps:

[0060] S101. Detect candidate obstacles in point cloud data.

[0061] In this application, point cloud data may be a collection of three-dimensional coordinate vectors recorded in the form of point clouds by radar scanning the scene where it is located, and each three-dimensional coordinate vector may be represented by (x, y, z). In addition, th...

no. 2 example

[0073] Figure 2A is a flow chart of a point cloud data denoising method according to the second embodiment of the present application, Figure 2B-2C is a schematic diagram of judging the spatial occlusion relationship of candidate obstacles according to the second embodiment of the present application. This embodiment is further optimized on the basis of the foregoing embodiments, and provides a possible implementation manner of determining the spatial occlusion relationship of candidate obstacles. Specifically, the specific situation of determining whether a candidate obstacle is a non-occlusion floating relationship is given. Such as Figures 2A-2C As shown, the method may specifically include:

[0074] S201. Detect candidate obstacles in point cloud data.

[0075] S202, judging whether the height of the candidate obstacle relative to the ground is greater than a preset height, if yes, execute S203, if not, execute S205.

[0076] Optionally, the embodiment of the prese...

no. 3 example

[0093] Figure 3A is a flow chart of a point cloud data denoising method according to the third embodiment of the present application, Figure 3B is a schematic diagram of judging the spatial occlusion relationship of candidate obstacles according to the third embodiment of the present application. This embodiment is further optimized on the basis of the foregoing embodiments, and provides an implementable manner of determining the spatial occlusion relationship of candidate obstacles. Specifically, the specific situation of determining whether the candidate obstacle is a full occlusion relationship is given. Such as Figure 3A-3B As shown, the method may specifically include:

[0094] S301. Detect candidate obstacles in point cloud data.

[0095] S302. Determine reference obstacles of candidate obstacles.

[0096] Wherein, the reference obstacle may be an obstacle appearing between the radar bearing device and the candidate obstacle within the radar viewing angle. It sh...

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 denoising method, device and equipment and a storage medium, and relates to the field of automatic driving. According to the specific implementation scheme, the method comprises the steps: detecting candidate obstacles in cloud data; selecting a noise obstacle from the candidate obstacles according to the spatial occlusion relationship of the candidate obstacles; and performing denoising processing on the point cloud data according to the noise obstacle. According to the embodiment of the invention, the noise obstacle in the candidate obstacle is determined according to the spatial occlusion relation of the candidate obstacle, floating noise and secondary reflection noise in the point cloud data can be accurately removed, the denoising precision and efficiency of the point cloud data are improved, and the accuracy and real-time performance of the obstacle sensing process are further improved.

Description

technical field [0001] The embodiments of the present application relate to the field of data processing, in particular to the field of automatic driving technology, and in particular to a point cloud data denoising method, device, device and storage medium. Background technique [0002] LiDAR is an important part of autonomous driving technology, and the point cloud data obtained by scanning can be used for obstacle perception. Due to the influence of lidar hardware, there will be some noise in the point cloud data. At present, when the existing technology performs obstacle perception, it first uses the whole frame denoising method to remove the noise in the point cloud data, and then performs obstacle detection. The commonly used whole frame denoising method has the whole frame point cloud data Perform processing such as Fourier transform or Hough transform, or directly use mean filtering or Gaussian filtering to iteratively denoise the entire frame of point cloud data. ...

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): G06T5/00G06K9/62
CPCG06T2207/10028G06T2207/10044G06F18/241G06T5/70
Inventor 王昊李晓晖王亮马彧
Owner BEIJING BAIDU NETCOM SCI & TECH 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