Method and device for identifying traffic signs

A traffic sign and recognition method technology, which is applied in the field of image target recognition, can solve the problems of missing traffic signs, shifting the color distribution of traffic sign images, reducing the accuracy of traffic sign recognition, etc., to achieve the effect of improving the recognition rate and overcoming the impact

Active Publication Date: 2014-08-06
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF4 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, there are certain technical defects in the above method, which may lead to a decrease in the accuracy of traffic sign recognition: there are complex illumination changes in natural images, which will cause a large shift in the color distribution of traffic sign images, a

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
  • Method and device for identifying traffic signs
  • Method and device for identifying traffic signs
  • Method and device for identifying traffic signs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 It is a flow chart of the traffic sign recognition method provided by Embodiment 1 of the present invention.

[0028] This embodiment can be used in the street view mode of the electronic map to detect the real scene photos in the street view mode, find out the traffic signs therein, and enrich the information displayed in the street view photos. This method can be executed by the electronic map data server, Such as figure 1 As shown, the method includes:

[0029] 110. According to the collected original color image of the traffic sign, acquire a grayscale information image and a color information image of the original color image.

[0030] Among them, the original color image can be a real-scene photo, for example, in the street view mode of the existing electronic map, the street view is composed of multiple real-scene photos, and the way of collecting the real-scene photos is usually taken by cameras, cameras and other equipment at the actual location , s...

Embodiment 2

[0049] figure 2 It is a flow chart of the traffic sign recognition method provided by Embodiment 2 of the present invention.

[0050] Such as figure 2 As shown, on the basis of the above-mentioned embodiments, the traffic sign recognition method provided by the embodiment of the present invention can perform shape recognition on the sign shape map, and obtain the region of interest in the sign shape map is preferably:

[0051] 210. Calculate gradient vectors of pixels in the logo shape map.

[0052] This operation regards the logo shape map as a coordinate system, that is, the image is the distribution of multiple pixel points on a two-dimensional plane, so the image can be regarded as a two-dimensional function. The gradient vector is a two-dimensional vector, the meaning of the gradient direction is the fastest changing direction of the gray level on the two-dimensional plane, and the gradient value is the rate of change in the fastest changing direction.

[0053] 220. ...

Embodiment 3

[0072] Figure 5 It is a flow chart of the traffic sign recognition method provided by the third implementation of the present invention.

[0073] Such as Figure 5 As shown, the traffic sign recognition method provided by the embodiment of the present invention is based on the above-mentioned embodiments, before classifying the region of interest based on the sample template and determining the corresponding traffic sign according to the classification result, it also includes:

[0074] 510. Acquire a clear frontal image of the set traffic sign, and generate at least two images under illumination and / or at least viewing angle conditions as training samples.

[0075] In the above embodiments, the sample model is generated using standard traffic sign images and machine learning methods, so the recognition ability of the sample model depends on the quality and quantity of training samples. This operation is the process of performing illumination processing on the standard traf...

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 provides a method and device for identifying traffic signs. The method comprises the steps that according to collected original color images of the traffic signs, gray level information images and color information images of the original color images are obtained; the color information images are filtered through the gray level information images, so that sign shape images are obtained; shape identification is conducted on the sign shape images, so that areas of interest in the sign shape images are obtained; based on a sample template, the areas of interest are classified and the corresponding traffic signs are determined according to classification results. According to the method and device for identifying the traffic signs, influence on real photos by the lighting condition is avoided and the identification rate of the traffic signs is improved.

Description

technical field [0001] Embodiments of the present invention relate to image target recognition technology, and in particular to a traffic sign recognition method and device. Background technique [0002] The detection and recognition of traffic signs is widely used in navigation and map technology. It belongs to the category of image target recognition, and its purpose is to detect and locate the circular traffic signs in the image. [0003] The current mainstream traffic sign recognition methods usually decompose the recognition of circular traffic signs into two steps of detection and filtering, that is, first use color or shape features to detect and locate the area of ​​interest in traffic signs from the collected color images; and then Then further filter the area of ​​interest to determine whether it is a real traffic sign. [0004] There are many specific means to realize the detection link: Generally, the image is converted from RGB (red-green-blue, red-green-blue) ...

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): G06K9/62
Inventor 艾锐郎咸朋
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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