High-precision direction signboard target extraction method based on point cloud

A target extraction and signage technology, applied to instruments, character and pattern recognition, computer components, etc., to achieve the effect of speeding up, reducing workload and saving time

Active Publication Date: 2020-09-22
WUHAN ZHONGHAITING DATA TECH CO LTD
View PDF10 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problems existing in the prior art, the present invention provides a point cloud-based high-precision direction sign target extraction method, which mainly solves

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
  • High-precision direction signboard target extraction method based on point cloud
  • High-precision direction signboard target extraction method based on point cloud
  • High-precision direction signboard target extraction method based on point cloud

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such as figure 1 As shown, the present invention provides a method for extracting a high-precision direction signboard target based on a point cloud, comprising the following steps:

[0050] S1, RGB image signboard attribute information extraction: obtain the point cloud data and RGB picture information of the signboard, and obtain the trajectory information of the vehicle, and perform thinning processing on the RGB picture according to the trajectory information to form a picture data set, and use the training A good target detection deep learning model extracts the position information and attribute information of the signboard from the picture data set. Attribute information such as speed limit, turning, U-turn and other content information on traffic signs.

[0051] S2, Rough extraction of signboards from RGB images: Detect the shape attributes of the signboards through the trained deep learning model for shape detection, and associate the shape attributes of the s...

Embodiment 2

[0076] Such as Figure 2~3 As shown, on the basis of the method provided in the first embodiment, this embodiment provides a point cloud-based high-precision direction sign object extraction device for implementing the method in the first embodiment. The computer environment used in this embodiment is windows10, the graphics card is GTX1080Ti, the software development environment is pycharm and adaconda, and the deep learning development environment is pytorch.

[0077] The device provided in this embodiment includes:

[0078] The RGB picture signboard attribute information extraction module is used to: obtain the point cloud data and RGB picture information of the signboard, and obtain the track information of the vehicle, and perform thinning processing on the RGB picture according to the track information to form a picture data set, Using the trained target detection deep learning model to extract the position information and attribute information of the signboard from the...

Embodiment 3

[0101] Such as Figure 4 As shown, the present embodiment provides a point cloud-based high-precision direction sign target extraction device, including:

[0102] memory for storing computer software programs;

[0103] The processor is used to read and execute the computer software program to realize the point cloud-based high-precision direction sign target extraction method described in Embodiment 1, for example, including: obtaining point cloud data and RGB pictures of the sign information, and obtain the track information of the vehicle, thin the RGB picture according to the track information to form a picture data set, and use the trained target detection deep learning model to extract the position of the signboard from the picture data set information and attribute information; detect the shape attribute of the signboard through the trained shape detection deep learning model, associate the shape attribute of the signboard with the point cloud data through the track inf...

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 relates to a high-precision direction signboard target extraction method based on point cloud. The method comprises the steps of acquiring point cloud data, RGB picture information and track information of a signboard, and thinning RGB pictures according to the track information to form a picture data set, and extracting position information and attribute information of the signboardfrom the picture data set through a target detection deep learning model; detecting the shape attribute of the signboard through another deep learning model, associating the shape attribute of the signboard into the point cloud data through the track information, and storing the point cloud data as a point cloud data set in a classified manner; converting the point cloud data in the point cloud data set into a point cloud picture, and predicting contour information of the point cloud picture by utilizing a semantic segmentation deep learning model; back-projecting the point cloud picture intothe point cloud data set according to a mapping relationship, and finely extracting shape points with inaccurate contour points according to the strength information of the point cloud data; and associating and storing the attribute information and the form points through the position information. According to the invention, the time for manually extracting the traffic elements in the signboard is reduced.

Description

technical field [0001] The invention relates to the field of high-precision map production and generation, in particular to the generation of digital map elements, and in particular to a point cloud-based high-precision direction sign target extraction method. Background technique [0002] High-precision maps, generally speaking, are electronic maps with higher precision and more data dimensions. The higher accuracy is reflected in the accuracy to the centimeter level, and the data dimension is more reflected in the fact that it includes surrounding static information related to traffic in addition to road information. High-precision maps store a large amount of driving assistance information as structured data, such as fixed object information around the lane, such as traffic signs, traffic lights and other indication information. [0003] In the production process of high-precision map elements, there are currently two methods for producing high-precision map sign informa...

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): G06K9/00G06K9/34G06K9/62
CPCG06V20/582G06V10/267G06F18/241
Inventor 何云熊迹李汉玢刘奋
Owner WUHAN ZHONGHAITING DATA TECH 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