Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Traffic signboard detection method based on deep learning

A technology of traffic signs and detection methods, which is applied in the field of traffic sign detection based on deep learning, can solve the problems of poor generalization ability and inability to realize accurate identification of traffic signs, and achieve good generalization ability and strong portability Effect

Inactive Publication Date: 2021-08-17
四川九通智路科技有限公司
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because it is learned based on a cascaded network, it is impossible to achieve accurate recognition of traffic signs in all-weather scenes, and the generalization ability is poor.

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 signboard detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] see figure 1 , a traffic sign detection method based on deep learning, comprising the following steps:

[0065] a. Using the Chinese traffic sign detection data set as the basic data set, collect pictures of traffic sign boards on the road under various weather and light conditions, and carry out target detection and classification labeling, which is used to expand the sample data set;

[0066] b. Carry out data preprocessing on the image through the image processing module, and the data preprocessing includes random cropping, left-right flipping, up-down flipping, contrast transformation, hue transformation, saturation transformation and Mosaic image enhancement;

[0067] c. After data preprocessing, use the YOLOv3 model in target detection as the detection network, and perform model building, model training and model tuning in sequence to complete the training;

[0068] d. Input the picture to be detected into the trained model to obtain the prediction result of the ...

Embodiment 2

[0071] see figure 1 , a traffic sign detection method based on deep learning, comprising the following steps:

[0072] a. Using the Chinese traffic sign detection data set as the basic data set, collect pictures of traffic sign boards on the road under various weather and light conditions, and carry out target detection and classification labeling, which is used to expand the sample data set;

[0073] b. Carry out data preprocessing on the image through the image processing module, and the data preprocessing includes random cropping, left-right flipping, up-down flipping, contrast transformation, hue transformation, saturation transformation and Mosaic image enhancement;

[0074] c. After data preprocessing, use the YOLOv3 model in target detection as the detection network, and perform model building, model training and model tuning in sequence to complete the training;

[0075] d. Input the picture to be detected into the trained model to obtain the prediction result of the ...

Embodiment 3

[0082] see figure 1 , a traffic sign detection method based on deep learning, comprising the following steps:

[0083] a. Using the Chinese traffic sign detection data set as the basic data set, collect pictures of traffic sign boards on the road under various weather and light conditions, and carry out target detection and classification labeling, which is used to expand the sample data set;

[0084] b. Carry out data preprocessing on the image through the image processing module, and the data preprocessing includes random cropping, left-right flipping, up-down flipping, contrast transformation, hue transformation, saturation transformation and Mosaic image enhancement;

[0085] c. After data preprocessing, use the YOLOv3 model in target detection as the detection network, and perform model building, model training and model tuning in sequence to complete the training;

[0086] d. Input the picture to be detected into the trained model to obtain the prediction result of 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 discloses a traffic signboard detection method based on deep learning, and belongs to the technical field of computer vision image processing. The method is characterized in that the method comprises the following steps: a, collecting pictures of traffic signboards on a road under various weather and illumination conditions, and carrying out target detection and classified label labeling; b, performing data preprocessing on the image through an image processing module; c, after data preprocessing, adopting a YOLOv3 model in target detection as a detection network, and sequentially performing model building, model training and model tuning to complete training; d, inputting a to-be-detected picture into the trained model to obtain a prediction result of the signboard position and the classification label in the current picture. According to the method, the YOLOv3 model is used as a detection network, model building, model training and model optimization are carried out in sequence, accurate identification of the traffic sign in an all-weather scene can be realized, and the method has good generalization ability.

Description

technical field [0001] The present invention relates to the technical field of computer vision image processing, in particular to a method for detecting traffic signs based on deep learning. Background technique [0002] With more and more vehicles on the road now, in the field of intelligent transportation, especially in the field of automatic driving, when the vehicle is driving on the road, it will encounter traffic signs, which contain rich road traffic information, providing drivers Provide warning and instruction auxiliary information, which plays an important auxiliary role in reducing the driving pressure of the driver and reducing the traffic pressure on the road. Therefore, if the traffic signs can be accurately identified, it is very important for traffic safety. In the traditional traffic sign recognition and detection task, the main method is to extract the information on the sign based on edge detection plus Hough transform, where the edge of the image refers ...

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): G06K9/00G06K9/62G06T7/90G06N3/04G06N3/08
CPCG06T7/90G06N3/04G06N3/08G06T2207/20081G06T2207/20084G06V20/582G06F18/24G06F18/253G06F18/214
Inventor 申莲莲吴彩萍邓承刚高鹏飞叶琳龚绍杰
Owner 四川九通智路科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com