Check patentability & draft patents in minutes with Patsnap Eureka AI!

Real-time recognition method of live panoramic traffic signs

A traffic sign and recognition method technology, applied in the field of image recognition, can solve the problem that the target recognition method cannot accurately detect and recognize traffic signs in real time and so on.

Active Publication Date: 2021-06-15
GUILIN UNIV OF ELECTRONIC TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] What the present invention aims to solve is the problem that the existing target recognition method cannot accurately detect and identify traffic signs in real time, and provides a real-time recognition method for live panorama traffic signs

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
  • Real-time recognition method of live panoramic traffic signs
  • Real-time recognition method of live panoramic traffic signs
  • Real-time recognition method of live panoramic traffic signs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in combination with specific examples and with reference to the accompanying drawings.

[0045]Aiming at the problem that in the environment of live panoramic traffic signs, the captured traffic signs are all images with large resolution, and it is difficult to accurately detect and identify small targets such as traffic signs in real time. This invention proposes a live panoramic view based on deep learning. The real-time recognition method of traffic signs, which is based on the YOLOv3 (You Only Look Once) target detection algorithm for network training and testing, can finally achieve real-time detection and recognition of traffic signs. In the first aspect, it provides a suitable network input size and a method to ensure that the training set is not aliased and undistorted. In the second aspect, a data enhan...

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 real-time recognition method of live panoramic traffic signs. Aiming at the large-resolution panoramic traffic images collected in real time, the proposed data processing method is used to extract the training set, and the proposed TSNet network is trained and fine-tuned. In the detection stage After image scaling based on the image pyramid, the sliding window processing method and the DS-NMS algorithm are used to ensure the real-time recognition of the target and improve the accuracy, so that the traffic signs can be quickly and accurately recognized in the live panoramic state.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method for real-time recognition of live panoramic traffic signs. Background technique [0002] With the popularity of unmanned driving and intelligent transportation systems, traffic signs, as an important part of road traffic, play an indispensable role. The real-time recognition of traffic signs plays a role in promoting the emerging fields of vision systems such as unmanned driving. The intelligent traffic assisted driving system can accurately detect and identify key road information in complex road information. In terms of unmanned driving research, the real-time recognition system of traffic signs can transmit some important road traffic information to the driving system, and then guide unmanned vehicles to make correct driving judgments, so as to realize the safe driving of unmanned vehicles. [0003] Existing target recognition methods are all aimed at large...

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): G06K9/00G06K9/34G06K9/62G06T3/40G06T9/00
CPCG06T3/40G06T9/00G06T2207/20021G06T2207/20081G06T2207/20084G06V20/582G06V10/267G06V2201/09G06F18/23213G06F18/253G06F18/214
Inventor 张向利孟祥松闫坤张红梅
Owner GUILIN UNIV OF ELECTRONIC TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com