Signboard identification method and device for automatic driving

An automatic driving and signage technology, applied in the field of navigation, can solve the problems of positioning technology error, position deviation of signboard apex, inability to accurately identify signboards, etc., and achieve the effect of improving accuracy, avoiding too small, and optimizing reliability

Active Publication Date: 2021-09-17
智道网联科技(北京)有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the signage recognition technology of related technologies is limited by software and hardware such as deep learning models and cameras. There are also errors in the positioning technology of the map

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
  • Signboard identification method and device for automatic driving
  • Signboard identification method and device for automatic driving
  • Signboard identification method and device for automatic driving

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 It is a schematic flowchart of the identification plate recognition method for automatic driving shown in the embodiment of the present application.

[0053] see figure 1 , a identification plate recognition method for automatic driving, comprising:

[0054] In step S101, the bounding box of the identification plate and a plurality of vertices of the bounding box are acquired.

[0055] In one embodiment, the self-driving vehicle is provided with a photographing device, which includes but is not limited to a monocular camera. The monocular camera is arranged at a suitable position of the vehicle. For example, the monocular camera can be arranged at the front windshield of the vehicle or at the rearview mirror of the vehicle, so that the monocular camera can photograph images containing road signs during the automatic driving of the vehicle. image.

[0056] In one embodiment, the bounding box of the signboard and multiple vertices of the bounding box can be o...

Embodiment 2

[0070] figure 2 It is another schematic flowchart of the identification plate recognition method for automatic driving shown in the embodiment of the present application.

[0071] see figure 2 , a identification plate recognition method for automatic driving, comprising:

[0072] In step S201, the bounding box of the identification plate and a plurality of vertices of the bounding box are acquired.

[0073] For this step, reference may be made to the description of step S101, which will not be repeated here.

[0074] In step S202, according to the bounding box of the signage, an image including a width of n pixels outside the bounding box is acquired, where n is a positive integer greater than the statistical pixel offset error value of the bounding box identified by the deep learning model.

[0075] In one embodiment, as Figure 4 As shown, the lower right corner of the bounding box 401 of the signboard outputted by the deep learning model according to the signboard ima...

Embodiment 3

[0092] image 3 It is another schematic flowchart of the identification plate recognition method for automatic driving shown in the embodiment of the present application.

[0093] see image 3 , a identification plate recognition method for automatic driving, comprising:

[0094] In step S301, the bounding box of the identification plate and a plurality of vertices of the bounding box are acquired.

[0095] For this step, reference may be made to the description of step S101, which will not be repeated here.

[0096] In step S302, according to the bounding box of the signage, an image including a width of n pixels outside the bounding box is acquired, where n is a positive integer greater than the statistical pixel offset error value of the bounding box identified by the deep learning model.

[0097] For this step, reference may be made to the description of step S202, which will not be repeated here.

[0098] In step S303, a plurality of corner blocks are generated on the...

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 signboard identification method and device for automatic driving. The method comprises the following steps: acquiring a bounding box of a signboard and a plurality of vertexes of the bounding box; according to the bounding box of the signboard, obtaining an image including n pixel widths outside the bounding box, n being a positive integer greater than a statistical pixel offset error value of the bounding box identified by the deep learning model; generating a plurality of corner blocks on the image, wherein each corner block of the plurality of corner blocks takes each vertex of the plurality of vertexes as the center, 2m + 1 pixels are the side length, and m is a positive integer smaller than n; obtaining edge information of each corner block according to the gradient information of each corner block of the plurality of corner blocks; according to the edge information of each corner block, obtaining an intersection point of each corner block; and obtaining the bounding box of the signboard again according to the intersection point of each angular point block. According to the scheme provided by the invention, the bounding box of the signboard can be accurately obtained, and the accuracy of obtaining the vertex position of the signboard is improved.

Description

technical field [0001] The present application relates to the technical field of navigation, and in particular to a method and device for identifying a signboard for automatic driving. Background technique [0002] With the development of autonomous driving technology, integrated navigation systems of related technologies such as GNSS / IMU integrated navigation systems cannot provide accurate and reliable positioning results in many special scenarios, which further affects subsequent planning and control. GNSS (Global Navigation Satellite System, Global Navigation Satellite System) is a satellite-based satellite positioning system, and the IMU navigation system is an inertial navigation system based on IMU (Inertial Measurement Unit, Inertial Measurement Unit). [0003] The high-precision map-based positioning technology of the related technology can extract the road factors (such as signs, lane lines, etc.) obtained by the visual sensor from the visual information, match the...

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): G06K9/00G06K9/46G06K9/62
CPCG06F18/22
Inventor 李岩张海强李成军
Owner 智道网联科技(北京)有限公司
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