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

Traffic sign recognizing method based on multi-resolution convolution neural networks

A convolutional neural network and traffic sign recognition technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problem of not being able to balance speed and accuracy, and achieve the effect of improving training speed

Active Publication Date: 2015-04-22
DALIAN UNIV OF TECH
View PDF2 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] The technical problem to be solved in the present invention is the problem that speed and accuracy cannot be taken into account when using convolutional neural network for traffic sign recognition, and a traffic sign recognition method based on multi-resolution convolutional neural network is proposed

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 recognizing method based on multi-resolution convolution neural networks
  • Traffic sign recognizing method based on multi-resolution convolution neural networks
  • Traffic sign recognizing method based on multi-resolution convolution neural networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046]

[0047] 1, determine training set, what the present invention selects is the training set in GTSRB (Germany traffic sign recognition benchmark, German traffic sign recognition benchmark), comprises training picture 39,209 pieces, test picture 12630 pieces.

[0048] 2. Preprocess the pictures in the training set. The steps are to first process them into grayscale images, and then normalize them into pictures with a uniform resolution of 48*48, and then back up these pictures to cut out the central area. A cropped image with a resolution of 36*36, attached figure 1 Input samples for two different resolutions of the example, and start training with these two parts of the image as two inputs.

[0049] 3. Select a training group; randomly select 50 samples each time from the sample set as a training group.

[0050] 4. Put each weight v ij ,w jk and threshold θ k , set to a small random value close to 0, and initialize the precision control parameters ε, learning r...

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 belongs to the technical field of computer applying and the subfield of the machine learning theories and application and focuses on the traffic sign recognizing problem in the intelligent traffic technology. A traffic sign recognizing method based on multi-resolution convolution neural networks is characterized by solving the problem that the speed is low when the convolution neural network is used for recognizing traffic signs, two-dimensional images with different resolutions are used as input, the two convolution neural networks with the same structure are operated in parallel to carry out feature mapping and extracting, and accurate classifying and recognizing are carried out based on a weight threshold value trained by the networks. The two CNNs with different resolution branches are used for replacing a basic CNN structure, the overall and outline features can be mapped through the high-resolution image input, the local and detailed features can be mapped through the low-resolution images, the recognizing resolution is guaranteed, and the model training speed is increased.

Description

technical field [0001] The invention belongs to the subfield of machine learning theory and application in the field of computer application technology, and the patent of the invention focuses on the traffic sign recognition problem in intelligent transportation technology. A multi-resolution convolutional neural network traffic sign recognition method is proposed to solve the problem of slow speed when using convolutional neural network for traffic sign recognition. Two-dimensional images with different resolutions are used as input, and two identical The convolutional neural network of the structure performs feature mapping and extraction, and then performs precise classification and identification based on the weight threshold value trained by the network. It not only ensures the diversity of extracted image features, but also improves the computing speed of the network, effectively taking into account the recognition accuracy and recognition speed. Background technique ...

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): G06K9/66
CPCG06V20/582G06F18/214
Inventor 葛宏伟谭贞刚孙亮何鹏程
Owner DALIAN UNIV OF TECH
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