Deep learning and image processing fused traffic signal lamp fault detection method

A traffic signal and image processing technology, applied in neural learning methods, traffic control supervision, instruments, etc., can solve the problems of missed detection, weak generalization ability of detection models, and low model recognition accuracy, and achieve the effect of improving accuracy.

Pending Publication Date: 2020-12-29
ZHEJIANG SUPCON INFORMATION TECH CO LTD
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention mainly solves the problems of weak detection model generalization ability, low model recognition accuracy and missed detection in the detection process in the existing video detection method; it provides 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
  • Deep learning and image processing fused traffic signal lamp fault detection method
  • Deep learning and image processing fused traffic signal lamp fault detection method
  • Deep learning and image processing fused traffic signal lamp fault detection method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0118]Embodiment 1: A method for detecting faults in traffic lights using deep learning and image processing, such asfigure 1 As shown, including the following steps:

[0119](1-1) Obtain the electronic police video stream under sunny, cloudy and rainy days, decode the electronic police video stream, and get the traffic signal image information, the position information of the traffic signal lamp group in the image, and the signal lights in the traffic signal lamp group Type information and location information;

[0120](1-2) Configure traffic signal light group information and each signal light information in the light group:

[0121](1-2-1) Configure semaphore group information:

[0122]Set the detection area and lamp group area of ​​the signal lamp group, if the detected signal lamp position is within the set lamp group area, then the type and position information of the signal lamp will be counted in the set lamp group area;

[0123]Such asfigure 2 As shown, considering the jitter and offset o...

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 deep learning and image processing fused traffic signal lamp fault detection method. The method comprises the following steps: S1, obtaining an electronic police video streamunder various weather conditions, and decoding the electronic police video stream to obtain a traffic signal lamp image, position information of a traffic signal lamp group in the image, and type information and position information of each signal lamp in the traffic signal lamp group; S2, configuring traffic signal lamp group information and information of each signal lamp in the lamp group; andS3, establishing a traffic signal lamp detection model. According to the invention, the problems of jittering and position deviation of a small-range camera are effectively solved, and the alarm accuracy is improved; and a deep learning technology based on a convolutional neural network is adopted to realize position and state identification of the signal lamp, and an image processing algorithm based on a signal lamp period is adopted to further improve the identification accuracy of the signal lamp.

Description

technical field [0001] The invention relates to the technical field of traffic signal lamp status monitoring, in particular to a traffic signal lamp fault detection method integrated with deep learning and image processing. Background technique [0002] Traffic lights are a category of traffic safety products that can be used to strengthen road traffic management and improve road use efficiency. The normal operation of traffic lights is the basis for the normal operation of the city, but at present, a large number of existing traffic lights are non-intelligent traffic lights without fault self-diagnosis capabilities. The fault detection of such traffic lights is mainly through the maintenance of the traffic police on duty, and the patrol inspection of traffic facilities units. and public alarms. [0003] The above signal lamp fault detection method has problems such as heavy workload of maintenance personnel, untimely fault detection, and low efficiency. In view of the act...

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): G06K9/00G06K9/46G06K9/62G08G1/097G06N3/04G06N3/08
CPCG08G1/097G06N3/08G06V10/56G06N3/045G06F2218/12G06F2218/08G06F18/2415Y02B20/40
Inventor 徐震辉祁照阁蒋栋奇曹锋袁旖马建国徐茂军
Owner ZHEJIANG SUPCON INFORMATION TECH 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