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

Traffic light detection method and device based on video

A technology of traffic signal lights and video, applied in the field of intelligent transportation, can solve the problems of abnormal signal lights and the inability to cover the color changes of traffic signal lights, etc., to reduce project costs, avoid excessive length, and ensure accuracy.

Inactive Publication Date: 2011-12-28
北京数字智通科技有限公司
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The adjustment of the brightness and chromaticity of the traffic signal light area by the system through video is largely a threshold judgment based on experience, which cannot cover the color change of the traffic signal light under various lighting conditions, so in some special environments Semaphore detection in

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
  • Traffic light detection method and device based on video
  • Traffic light detection method and device based on video
  • Traffic light detection method and device based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The present invention provides a video-based traffic signal detection method and device, the core idea of ​​which is to obtain the color feature attributes of sampling pixels in video images; and map the color feature attributes of sampling pixels to high Dimensional space, do dot product operation with the support vectors of various color categories; the recognition model is obtained by collecting sample data training of each color of the traffic signal light under different lighting conditions; according to the result of the dot product operation, the sampling pixels are detected The color of the corresponding traffic light. The present invention recognizes the color of the traffic signal light through the real-time video image, and realizes the real separation of the intelligent traffic monitoring system and the traffic signal light. Long, difficult construction and maintenance problems, thus reducing the project cost. And the present invention obtains the recogniti...

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 video-based traffic signal lamp detection method and device, belonging to the technical field of intelligent transportation. The detection method includes: obtaining the color characteristic attribute of the sampling pixel in the video image; mapping the color characteristic attribute of the sampling pixel to a high-dimensional space through a pre-trained recognition model, and performing a dot product operation with the support vectors of various color categories The recognition model is obtained by training sample data of various colors of traffic lights under different lighting conditions; according to the result of the dot product operation, the color of the traffic lights corresponding to the sampling pixels is detected. The present invention recognizes the color of the traffic signal light through the real-time video image, realizes the real separation of the intelligent traffic monitoring system and the traffic signal light; the method can adapt to the influence of various factors on the color of the traffic signal light in the real environment, and ensures the accuracy of the recognition result .

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, and more specifically, to a method and device for detecting traffic signal lights based on video. Background technique [0002] With the development of society and economy, cars play an indispensable role in people's daily life. However, the increasing number of cars also brings great challenges to urban traffic management, especially in first-tier cities. Intelligent transportation has become an important means of urban traffic management, among which the electronic police system has become the main way to realize urban road violation detection and traffic flow statistics. Traffic lights, as one of the input signals of the electronic police system, have become an important basis for traffic law enforcement management. [0003] At present, the existing traffic signal light detection methods can be divided into the following types: one is the traditional communication between t...

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): G08G1/097G06K9/66
Inventor 温炜晏峰范云霞延瑾瑜张滨张欢欢范友健李大鹏
Owner 北京数字智通科技有限公司
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