Point cloud detection method and device, computer equipment and storage medium

A detection method and point cloud technology, which is applied to computer parts, calculation, character and pattern recognition, etc., can solve the problems of less information and more noise in point cloud, and achieve the effect of enriching dimensions and improving accuracy

Pending Publication Date: 2020-09-25
GUANGZHOU WERIDE TECH LTD CO
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a point cloud detection method, device, computer equipment, and storage medium to solve the problems of less information and more noise in point clouds

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 detection method and device, computer equipment and storage medium
  • Point cloud detection method and device, computer equipment and storage medium
  • Point cloud detection method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] figure 2 It is a flow chart of a point cloud detection method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where image data is semantically analyzed according to time series and semantic information representing obstacles is given to the point cloud. This method can be composed of point cloud detection device, the point cloud detection device can be implemented by software and / or hardware, can be configured in computer equipment, for example, unmanned equipment such as unmanned vehicles, robots, unmanned aerial vehicles, and servers, personal Computing equipment such as computers, etc., the method specifically includes the following steps:

[0039] S201. Acquire multiple frames of point cloud and multiple frames of original image data that are simultaneously collected for the same visual range.

[0040] In this embodiment, the unmanned device is equipped with a laser radar and a camera, the laser radar is used to de...

Embodiment 2

[0073] image 3 It is a flow chart of a point cloud detection method provided by Embodiment 2 of the present invention. Based on the foregoing embodiments, this embodiment further refines semantic segmentation and adds processing operations for obstacle detection. The method specifically includes the following steps :

[0074] S301. Acquire multiple frames of point cloud and multiple frames of original image data that are simultaneously collected for the same visual range.

[0075] In this embodiment, the unmanned device can collect point cloud and original image data in real time, identify the semantic information of pixels for obstacles and assign it to the point cloud, so that the point cloud can be used to detect obstacles. In addition, the unmanned device can also collect After the point cloud and original image data, the point cloud and original image data are sent to the computing device, and the computing device recognizes the semantic information of the pixel point f...

Embodiment 3

[0147] Image 6 A schematic structural diagram of a point cloud detection device provided in Embodiment 3 of the present invention, the device may specifically include the following modules:

[0148] Raw data acquisition module 601, configured to acquire multi-frame point cloud and multi-frame original image data collected simultaneously for the same visual range;

[0149] The point cloud projection module 602 is used to respectively project the point clouds of multiple frames onto the original image data of multiple frames to obtain target image data of multiple frames;

[0150] The semantic segmentation module 603 is configured to perform semantic segmentation on the point cloud and pixels in the target image data according to the temporal relationship between multiple frames of the target image data, so as to identify the relationship between the pixels and the obstacles. semantic information;

[0151] The semantic information assignment module 604 is configured to assign...

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 detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring multiple frames of point clouds and multiple frames of original image data which face the same visual range and are acquired at the same time; respectively projecting the multiple frames of point clouds onto the multiple frames of original image data to obtain multiple frames of target image data; performing semantic segmentation on point clouds and pixel points in the target image data according to the time sequence relationship among the multiple frames of target image data so as to identify the semantic information of the pixel points for the obstacle; and endowing the semantic information of the pixel points with point clouds corresponding to the pixel points. The visual features of the image data are combined with the spatial features of the point cloud, the target image data not only contains rich color features and texture features, but also contains the coordinates of the point cloud, the laser intensity and other features, the dimensionality of the features is greatly enriched, and semantic segmentation is carried out by considering the time sequence between frames, so that the accuracy of semantic information of an obstacle is improved.

Description

technical field [0001] Embodiments of the present invention relate to environment sensing technology, and in particular to a point cloud detection method, device, computer equipment and storage medium. Background technique [0002] In scenarios such as automatic driving of vehicles and automatic inspection of robots, lidar, as a commonly used sensor, can detect point clouds of the surrounding environment to identify obstacles. [0003] The point cloud detected by lidar is relatively sparse and has a lot of noise. Each point cloud contains information such as laser intensity and coordinates. Problems such as wrong categories, for example, confusing people with pillars, and misidentifying noise generated by dust, water splashes, flying insects, etc. as obstacles. Contents of the invention [0004] Embodiments of the present invention provide a point cloud detection method, device, computer equipment, and storage medium to solve the problems of less information and more nois...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/36G06N3/04
CPCG06V20/56G06V10/20G06V10/267G06N3/044G06N3/045
Inventor 黄章帅杨欣豫陈世熹韩旭
Owner GUANGZHOU WERIDE TECH LTD CO
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