Target point cloud identification method and device, electronic equipment and storage medium

A target point and cloud recognition technology, applied in the computer field, can solve problems such as high manpower input costs, low efficiency, and difficulty in obtaining training data

Active Publication Date: 2020-09-01
BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The above recognition method based on deep learning training recognition model has the problem of difficulty in obtaining training data
However, the recognition method relying on the human naked eye is obviously inefficient and has high labor input costs.

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
  • Target point cloud identification method and device, electronic equipment and storage medium
  • Target point cloud identification method and device, electronic equipment and storage medium
  • Target point cloud identification method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a flow chart of a target point cloud recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the scene of recognizing a target point cloud in a single frame of point cloud data, and the target point cloud is specifically a pedestrian, for example. The point cloud of the vehicle, the point cloud of the vehicle, etc. In this embodiment, an explanation is made by taking the target point cloud as a point cloud of a pedestrian as an example. The method can be executed by a target point cloud recognition device, and the device can be realized by software and / or hardware.

[0031] Such as figure 1 As shown, the method specifically includes the following steps:

[0032] Step 110, acquiring single-frame point cloud data for building a map.

[0033] Wherein, the single-frame point cloud data generally refers to the point cloud data obtained by scanning a circle of the vehicle radar, that is, 360°.

[0034] Step 12...

Embodiment 2

[0058] figure 2 It is a flow chart of a target point cloud recognition method provided by Embodiment 2 of the present invention. On the basis of the above-mentioned embodiments, the above-mentioned step of "determining the target to be recognized based on the first target point cloud cluster" in this embodiment "Point cloud data" gives a specific implementation method to accurately identify the target point cloud. The explanations of terms that are the same as or corresponding to those in the foregoing embodiments are not repeated here.

[0059] see figure 2 The target point cloud recognition method provided in this embodiment specifically includes the following steps:

[0060] Step 210, acquiring single-frame point cloud data for building a map.

[0061] Step 220: Divide the single-frame point cloud data used to construct the map into ground point cloud data and non-ground point cloud data.

[0062] Step 230: Determine the height range according to the height characteri...

Embodiment 3

[0099] image 3 It is a flow chart of a target point cloud recognition method provided by Embodiment 3 of the present invention. This embodiment further optimizes the scheme on the basis of the above embodiments, specifically based on the fact that the target to be recognized is adjacent to the current frame The first position in the single-frame point cloud data used to build the map in the previous frame, and track the target to be identified in the current frame point cloud data, so as to quickly identify the target point cloud and reduce the candidates for subsequent further identification The amount of data in the point cloud, so as to achieve the purpose of improving the overall recognition efficiency and accuracy. The explanations of terms that are the same as or corresponding to those in the foregoing embodiments are not repeated here.

[0100] see image 3 The target point cloud recognition method provided in this embodiment specifically includes the following steps...

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 target point cloud identification method and device, equipment and a storage medium. The method comprises the steps of obtaining single-frame point cloud data used for constructing a map; dividing the single-frame point cloud data for constructing the map into ground point cloud data and non-ground point cloud data; and determining the point cloud data of a to-be-identified target from the non-ground point cloud data according to the feature attributes of the to-be-identified target. Through the technical scheme of the embodiment of the invention, the purpose of identifying the target point cloud is achieved.

Description

technical field [0001] The embodiments of the present invention relate to the field of computer technology, and in particular, to a target point cloud recognition method, device, electronic equipment and storage medium. Background technique [0002] The construction of high-precision maps is an important part of driverless technology. At present, commonly used high-precision maps include point cloud maps constructed based on point cloud data. The point cloud data is usually scanned by the vehicle radar and inertial navigation system according to the driving route. During the scanning process, moving objects such as cars and people on the road are inevitably scanned, so that the point cloud data obtained for building maps inevitably includes noise data such as cars and people. Therefore, in order to ensure the accuracy of the constructed point cloud map, it is necessary to eliminate the noise data in the point cloud data when constructing the point cloud map. The identific...

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): G06K9/00G06K9/62G06T5/00
CPCG06T5/002G06T2207/10028G06V20/00G06F18/23
Inventor 王冰
Owner BEIJING JINGDONG QIANSHITECHNOLOGY 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