Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and device for determining a traffic sign image

A technology for determining traffic signs and methods, applied in image analysis, image data processing, instruments, etc., can solve problems such as high missed detection rate and poor detection effect

Active Publication Date: 2017-07-11
WUHU LION AUTOMOTIVE TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of high missed detection rate and poor detection effect in the existing traffic sign determination method, the embodiment of the present invention provides a traffic sign image determination method and device

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
  • A method and device for determining a traffic sign image
  • A method and device for determining a traffic sign image
  • A method and device for determining a traffic sign image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] An embodiment of the present invention provides a method for determining a traffic sign image, see figure 1 , the method flow includes:

[0065] In step 101, the connected regions of each predetermined color in the RGB (three color channels of red, green and blue) image of the traffic sign image to be determined are determined.

[0066] Wherein, the predetermined color includes red, blue and yellow.

[0067] In step 102, a candidate traffic sign image is extracted from the RGB image for which the traffic sign image needs to be determined according to the determined connected regions.

[0068] In step 103, the edge of each candidate traffic sign image is extracted.

[0069] In step 104, the edge of each candidate traffic sign image is divided into several line segments.

[0070] In step 105 , the steering angles between two connected line segments in each edge and between adjacent line segments that are not connected but tend to intersect are calculated.

[0071] Whe...

Embodiment 2

[0077] An embodiment of the present invention provides a method for determining a traffic sign image, see figure 2 , the method flow includes:

[0078] In step 201, according to the transformation formula of each predetermined color, color transformation is performed on the RGB image to be determined as the traffic sign image, so as to obtain an image highlighting the predetermined color.

[0079] Wherein, the predetermined color includes red, blue and yellow. The transformation formula of red is C red =max(0,min((v R -v G ) / A,(v R -v B) / A)), the transformation formula of blue is C blue =max(0,min((v B -v R ) / A,(v B -v G ) / A)), the transformation formula of yellow is C yellow =max(0,min((v G -v B ) / A,(v R -v B ) / A)). C red Indicates the red image obtained after transformation, C blue Indicates the blue image obtained after transformation, C yellow Indicates the resulting yellow image after transformation. v R Indicates the R channel pixel value, v G Indi...

Embodiment 3

[0172] see Figure 5 , the embodiment of the present invention provides a device for determining a traffic sign image, the device includes a first determination module 301, a first extraction module 302, a second extraction module 303, a segmentation module 304, a calculation module 305 and a second determination module 306 .

[0173] The first determination module 301 is used to determine the connected area of ​​each predetermined color in the RGB image of the traffic sign image, and the predetermined color includes red, blue and yellow.

[0174] The first extraction module 302 is configured to extract candidate traffic sign images from the RGB image according to the determined connected regions.

[0175] The second extraction module 303 is used to extract the edge of each candidate traffic sign image.

[0176] The segmentation module 304 is used to segment the edge of each candidate traffic sign image into several line segments.

[0177] The calculation module 305 is 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
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method and a device for determining a traffic sign image, belonging to the field of automobiles. The method includes: determining the connected area of ​​each predetermined color in the RGB image of the traffic sign image to be determined, and the predetermined color includes red, blue and yellow; extracting the candidate traffic sign image from the RGB image according to the determined connected area ; extract the edge of each candidate traffic sign image; divide the edge of each candidate traffic sign image into several line segments; The steering angles between; according to the size of the steering angle in each edge, the traffic sign image is determined from the candidate traffic sign images. The device includes a first determination module, a first extraction module, a second extraction module, a segmentation module, a calculation module and a second determination module. The invention combines and utilizes the color and shape characteristics of the traffic sign, and has better effect when determining the image of the traffic sign.

Description

technical field [0001] The invention relates to the field of automobiles, in particular to a method and device for determining a traffic sign image. Background technique [0002] At present, in the upsurge of research on advanced driving assistance systems and unmanned vehicles, it is an indispensable research content to study how to identify various external environmental information in the vehicle driving environment. These external environmental information include lane lines, obstacles, structured or unstructured road surfaces, and traffic signs. Among them, the recognition of traffic signs is generally aimed at traffic signs of speed limit, warning and instruction. The existing methods for identifying traffic signs mainly use the information such as the shape of the traffic sign itself to analyze, determine the image of the traffic sign, and then specifically identify the image of the traffic sign. [0003] In the process of realizing the present invention, the invent...

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): G06T7/12G06K9/46
CPCG06T7/11G06V10/56
Inventor 谷明琴王海孙锐
Owner WUHU LION AUTOMOTIVE TECH CO LTD