Mileage signboard automatic recognition method for road video routing inspection

An automatic identification and signage technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of low efficiency, easy to be affected by geographical factors and environmental factors, large errors, etc., to achieve high detection accuracy , improve efficiency, improve the effect of accuracy

Active Publication Date: 2016-01-27
SOUTHWEST JIAOTONG UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The mileage sign is the key identification mark of the road section. When recording the fault information, it needs to be marked by the mileage sign. At present, the mainstream method of mileage sign recognition is still the naked eye, which is easily affected by geographical and environmental factors, and the error is large. ,low efficiency

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
  • Mileage signboard automatic recognition method for road video routing inspection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0038] Such as figure 1 As shown, a method for automatic identification of mileage signs for highway video inspection, comprising the following steps:

[0039] Obtain video data and convert video data into frame images;

[0040] Use a rectangular frame to select the mileage sign to divide the frame image into positive and negative sample areas, and correct the positive and negative samples;

[0041] Extract the gradient histogram feature operator of the positive and negative samples after correction, and train the feature vector into a classification model;

[0042] Set an all-zero matrix with the same size as the frame image to be tested as the probability density matrix; use the moving window technology and use the classification model of the feature vector to judge the samples to be tested in the window to form a standardized probability d...

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 mileage signboard automatic recognition method for road video routing inspection. The method comprises the following steps of obtaining video data, and converting the video data into a frame image; using a rectangular frame to select a mileage signboard for dividing the frame image into a positive sample region and a negative sample region, and performing positive and negative sample correction; extracting gradient histogram feature operators of corrected positive and negative samples, and training classification models from feature vectors; outputting a grayscale image of a probability density matrix; calculating a frame image to be tested to perform global binaryzation on a threshold; performing global binaryzation on the output probability density matrix grayscale image to find the maximum connected domain; cutting the corresponding maximum connected domain region ROI in the frame image to be tested; dividing the mileage signboard, and extracting the character region of the mileage signboard; and using wavelet packet texture features and combining a vector machine classifier for performing mileage signboard character recognition. The mileage signboard automatic recognition method has the advantages that the recognition efficiency is high; the accuracy is high; the influence by geographical factors and environment factors is avoided; and the existing hardware equipment is used, so that the cost is low.

Description

technical field [0001] The invention relates to a target automatic detection and recognition technology, in particular to an automatic recognition method for a mileage identification plate for highway video patrol inspection. Background technique [0002] In recent years, the scale and capacity of China's road transportation network have rapidly expanded, the structure has been continuously optimized, and the service level has been continuously improved. A relatively complete road transportation system has been established; The mileage of traffic has reached 96,000 kilometers; expressways cover more than 90% of the medium-sized cities in the country; The total mileage, highway passenger and freight volume, turnover volume and other indicators rank first in the world; reviewing the development history of China's highways and comparing the development trends of the world's highways, it can be considered that China's highway traffic is in a period of rapid development of expand...

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): G06K9/00G06K9/32
CPCG06V20/46G06V20/63
Inventor 唐鹏金炜东韦璞
Owner SOUTHWEST JIAOTONG UNIV
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