Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for extracting and identifying candidate areas of traffic lights in complex environments

A technology of traffic lights and candidate areas, which is applied in the fields of intelligent transportation and computer vision, can solve problems such as large calculation errors, inability to accurately determine object classification categories, and high complexity, and achieve strong timeliness, good portability, and refinement Enhanced effect

Active Publication Date: 2022-03-15
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is complex and cannot accurately determine the object classification category in the image
will lead to large calculation errors

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 for extracting and identifying candidate areas of traffic lights in complex environments
  • A method for extracting and identifying candidate areas of traffic lights in complex environments
  • A method for extracting and identifying candidate areas of traffic lights in complex environments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the implementation methods and accompanying drawings.

[0051] In order to solve the technical problem of accurate segmentation and extraction of traffic lights, the present invention detects and recognizes traffic lights targets by constructing an overall image depth perception model and combining video sequence target motion continuity. The construction of the depth perception model is based on the characteristics of the luminous traffic lights, combined with the structural features related to the traffic lights in the image and the overall color space distribution characteristics of the image. In this way, the cluttered background and the influence of light in the image can be effectively removed. After obtaining the depth perception model, the image of the perception model is segmented, ...

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 for extracting and identifying candidate areas of traffic signal lights in complex environments. When the present invention extracts the traffic signal candidate area, by avoiding the way of directly processing from the grayscale image, the processing of the image is carried out in the way of extracting the perceptual model of multi-layer image information and tensor structure. The redundant and cluttered areas in the original image are effectively removed, and a more accurate segmented image is obtained. At the same time, the time-domain cross-correlation information between associated elements is combined when extracting the associated image set to better retain the content of traffic lights in the image. In the recognition stage, the internal features of the tensor are extracted from the structure tensor built on the basis of the perceptual model, which effectively improves the recognition accuracy. The invention takes into account the target extraction under simple background and complex background, and has high accuracy and good robustness.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation and computer vision, and in particular relates to feature extraction, that is, detection processing of traffic signal lights. Background technique [0002] With the gradual popularization of automobiles, issues such as urban traffic safety and crossing efficiency have become increasingly prominent. In order to effectively reduce the probability of traffic accidents, road traffic signal recognition technology based on machine vision and pattern recognition technology has become an important research field of intelligent transportation systems, and it is also one of the key technologies and difficulties in the research of unmanned vehicles. The core of traffic signal recognition lies in the algorithm. At present, despite the rapid development of computer technology and artificial intelligence technology, the algorithm of target detection and recognition is constantly emerging, bu...

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): G06V20/58G06V10/56G06V10/25G06V10/764G06K9/62G06T7/11G06T7/136
Inventor 王正宁曾凡伟吕侠张翔何庆东赵德明陈远鹏
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com