Traffic sign recognition method and device and training method and device of neural network model

A traffic sign and traffic technology, applied in the field of image processing, can solve problems such as difficult to achieve accurate distinction, unable to effectively extract semantic information of traffic signs

Inactive Publication Date: 2020-08-04
MOMENTA SUZHOU TECH CO LTD
View PDF0 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are many types of traffic signs. Many of these traffic signs have similar appearance features. It is difficult to achieve accurate distinction by using existing image classification methods, and the semantic information in traffic signs cannot be effectively extracted, which is not conducive to the vehicle's understanding of traffic sign information. take advantage of

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
  • Traffic sign recognition method and device and training method and device of neural network model
  • Traffic sign recognition method and device and training method and device of neural network model
  • Traffic sign recognition method and device and training method and device of neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0119] see figure 1 , figure 1 It is a schematic flowchart of a neural network model training method provided by an embodiment of the present invention. The method can be applied to automatic driving, and is executed by a neural network model training device, which can be realized by means of software and / or hardware, and generally can be integrated in a vehicle-mounted computer, a vehicle-mounted industrial personal computer (Industrialpersonal Computer, IPC), etc. In the vehicle-mounted terminal, the embodiments of the present invention are not limited. The neural network model provided in this embodiment is mainly aimed at the preset target detection model used to identify simple traffic signs, where a simple traffic sign generally refers to a sign consisting of graphics, symbols or a small number of characters, such as warning signs, Prohibition signs, instruction signs, guide signs, tourist area signs, road construction safety signs and speed limit signs, etc. like fi...

Embodiment 2

[0144] see Figure 4 , Figure 4 It is a schematic flowchart of another neural network model training method provided by an embodiment of the present invention. The method can be applied to automatic driving, and can be executed by a neural network model training device, which can be realized by software and / or hardware, and generally can be integrated in a vehicle-mounted computer, a vehicle-mounted industrial personal computer (Industrialpersonal Computer, IPC), etc. In the vehicle-mounted terminal, the embodiments of the present invention are not limited. The neural network model provided in this embodiment is mainly aimed at the convolutional cyclic neural network model used to identify duplicated traffic signs. like Figure 5 As shown, the training method of the neural network model provided in this embodiment specifically includes:

[0145] S310. Obtain historical sub-images, category information, and semantic information of the historical road image that only contai...

Embodiment 3

[0182] see Figure 7 , Figure 7 It is a structural block diagram of a neural network model training device provided by an embodiment of the present invention. like Figure 7 As shown, the device includes: a historical road sample image acquisition module 510, a second training sample set generation module 520 and a preset target detection model training module 530, wherein,

[0183] The historical road sample image acquisition module 510 is configured to acquire the historical road sample image marked with the location information, category information and semantic information of the traffic sign;

[0184] The second training sample set generation module 520 is configured to extract the position information of the traffic sign in the historical road sample image, and generate a second training sample set based on a plurality of the position information and their corresponding category information and semantic information ;

[0185] The preset target detection model traini...

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 traffic sign recognition method and device, and a training method and device of a neural network model. The traffic sign recognition method comprises the steps: acquiring position information and category information of a current sub-image of a traffic sign board area in a current road image, wherein the position information and the category informationare obtained by conducting feature extraction on a to-be-recognized traffic sign board image in the current road image through a preset target detection model; according to the position information and the category information, performing feature extraction on the current sub-image by using a convolutional neural network (CNN) to obtain a feature sequence of the current sub-image; and obtaining target semantic information corresponding to the current sub-image according to the feature sequence and a preset convolutional recurrent neural network (CRNN) model, whereinthe CRNN model enables the feature sequence of the image to be associated with the corresponding semantic information. By adopting the technical scheme, the identification precision of the traffic sign is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a traffic sign recognition method, a neural network model training method and a device. Background technique [0002] With the development of current intelligent transportation technology, autonomous driving and assisted driving technology are receiving more attention. In the field of automatic driving and assisted driving, an accurate perception system is the prerequisite for all other systems to work correctly, and traffic plate recognition is an important function in the vehicle perception system. Accurate traffic plate recognition is the basis for vehicles to respond correctly to the environment, and plays a vital role in the normal and safe driving of autonomous vehicles. [0003] At present, there are many types of traffic signs. Many of these traffic signs have similar appearance features. It is difficult to achieve accurate distinction by using existing image cl...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/582G06N3/045G06F18/214
Inventor 李亚
Owner MOMENTA SUZHOU 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