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

Traffic sign recognition method and system based on cascade deep learning

A technology of traffic sign recognition and deep learning, applied in character and pattern recognition, instruments, computing, etc., can solve the problems of insufficient utilization of sample space and inability to effectively mine sample supervision information, so as to improve detection and recognition accuracy and make up for supervision The effect of insufficient sex

Active Publication Date: 2019-07-05
INST OF INFORMATION ENG CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the simple feature extraction method cannot adapt, so a relatively complex classifier such as a neural network is used for identification. However, the existing traffic detection and marking methods based on neural networks do not make full use of the sample space and cannot effectively explore the supervision of samples. information

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 system based on cascade deep learning
  • Traffic sign recognition method and system based on cascade deep learning
  • Traffic sign recognition method and system based on cascade deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0064] Based on the above method, the inventor has done relevant experimental verification, which is based on the evaluation of 43 traffic signs on the German Traffic Sign Recognition Benchmark (GTSRB), a German traffic sign standard database.

[0065] First, the classic convolutional neural networks LeNet-5, VGG-Net, and AlexNet were used as the basic convolutional networks of the framework, and then four sets of experiments were carried out, including only positive samples, adding random negative samples on the basis of positive samples, and adding The case of negative supervised samples. The traffic sign recognition rate in the GTSRB database is shown in the following table:

[0066] basic network Only positive samples random negative sample -1 Random Negative Sample - 2 Negative supervision samples LeNet-5 92.45％ 92.81％ 92.28％ 93.94％ VGG-Net 94.31％ 94.15％ 94.33％ 95.36％ AlexNet 95.19％ 95.20％ 95.33％ 96.69％

[0067] From the a...

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 present invention provides a traffic sign recognition method and system based on cascaded deep learning, which introduces the idea of ​​cascaded convolutional neural network, expands the target sign sample space, and adds more supervised samples, in order to make The recognition of traffic signs adds more prior information, so that the sample space for recognizer training has higher supervision. This method can make full use of various characteristic information of signs, make up for the deficiency of existing traffic sign recognition based on neural network, and improve the detection and recognition rate of signs.

Description

technical field [0001] The present invention relates to a computer vision and machine learning technology, which belongs to the method of target detection and recognition, in particular to a traffic sign recognition method and system based on cascade deep learning, which is suitable for the detection and recognition of traffic signs in images or videos . Background technique [0002] Traffic sign recognition is one of the most important modules of the current intelligent assisted driving system. During daily driving, drivers often ignore traffic signs due to obstacles or lack of energy, violate traffic rules and even cause car accidents. Therefore, traffic sign recognition is not just A technology is a major event related to the national economy and people's livelihood. [0003] Traffic sign recognition technology is a branch of target recognition, but it is different from traditional target recognition, but for a specific field of target recognition. At present, there are...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/582G06V2201/09G06F18/214G06F18/24G06F18/25
Inventor 葛仕明解凯旋罗朝叶奇挺孙利民
Owner INST OF INFORMATION ENG CHINESE ACAD OF SCI
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