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

Multi-characteristic layered traffic sign identification method

A traffic sign recognition and traffic sign technology, applied in the field of layered traffic sign recognition, can solve the problems of poor real-time performance and low accuracy, and achieve the effect of improving accuracy and real-time performance

Inactive Publication Date: 2013-11-13
CHERY AUTOMOBILE CO LTD
View PDF2 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention designs a multi-feature layered traffic sign recognition method, which solves the problems of low accuracy and poor real-time performance in traffic sign recognition

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
  • Multi-characteristic layered traffic sign identification method
  • Multi-characteristic layered traffic sign identification method
  • Multi-characteristic layered traffic sign identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] Combine below figure 1 , the present invention is further described:

[0015] figure 1 The flow chart of the multi-featured layered traffic sign recognition method of the present invention is provided, which is divided into two parts, recognition and training, and the main steps of the training part are as follows:

[0016] (1) put the standard The images of traffic signs are divided into three categories: prohibition signs, warning signs, and instruction signs.

[0017] (2) Extract the Histogram of Oriented Gradients (HOG) features of each type of image, that is, of pending images Take its luminance component and divide it into The overlapping sub-blocks, calculate the gradient of each block, divide 0 to 180 degrees into 9 directions to calculate the direction histogram, and form it after normalization Dimensional HOG features.

[0018] (3) Adaboost classifiers are used for T rounds of training for each type of traffic sign, and the training samples are set...

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 relates to a multi-characteristic layered traffic sign identification method. According to the multi-characteristic layered traffic sign identification method, multi-characteristic layered classified strategies from coarseness to fineness are designed, first color and shape characteristics are adopted to form coarse category judgment of a first layer, and then direction gradient histogram characteristics are extracted to be input into an adaboost integrated classifier to achieve fine identification. Multiple characteristics including colors, shapes and direction gradient histograms are adopted to improve accuracy in traffic sign identification.

Description

technical field [0001] The invention relates to an image recognition method in the field of computer vision, in particular to a layered traffic sign recognition method combining coarse and fine features of multiple features. Background technique [0002] Traffic signs are public signs that combine graphics and text, and are used to manage traffic and indicate driving directions to ensure smooth roads and safe driving. Traffic signs are an important carrier of traffic information, which can provide accurate traffic guidance to drivers and pedestrians. Timely and accurate identification of traffic sign information is crucial to traffic safety. Traffic sign recognition is the process of obtaining external road traffic images through image acquisition equipment, and then processing and classifying the acquired images. It can give instructions or early warnings to drivers in a timely manner, which is conducive to maintaining smooth traffic and preventing traffic accidents. occur...

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 Applications(China)
IPC IPC(8): G06K9/62G06K9/54
Inventor 孙锐王继贞陈军
Owner CHERY AUTOMOBILE CO LTD