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

Method for detecting vehicle flow of multiple lanes on basis of video analysis

A technology of traffic flow detection and video analysis, which is applied in the field of traffic parameter collection in intelligent transportation systems, can solve problems such as accurate detection of traffic flow, high detection accuracy, and inability to quickly adapt to scene changes, and achieve the effect of improving accuracy

Active Publication Date: 2017-01-25
ZAOZHUANG UNIV
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Existing technologies are mainly aimed at expressway, expressway, weather environment, and road environment with good and clean vehicle detection, and cannot quickly adapt to scene changes and maintain a high detection accuracy rate under conditions such as rapid changes in weather and lane environments, etc. ; Existing technology cannot accurately detect traffic flow at intersections with dense vehicles, when vehicles press lines, change lanes, etc.

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
  • Method for detecting vehicle flow of multiple lanes on basis of video analysis
  • Method for detecting vehicle flow of multiple lanes on basis of video analysis
  • Method for detecting vehicle flow of multiple lanes on basis of video analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly describe the accompanying drawings that need to be used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some specific embodiments of the present invention , for those skilled in the art, according to the spirit of the present invention, other drawings can also be obtained according to these drawings.

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

[0043] Multi-lane traffic flow detection method based on video analysis, the flow chart is as follows figure 1 , which includes the following steps:

[0044] Step 1: Input a video image to establish a video background model, and establish an initial background model b(x, y) by...

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 relates to a method for detecting vehicle flow of multiple lanes on the basis of video analysis, and belongs to the field of acquisition of traffic parameters of intelligent traffic systems. The technical scheme includes that the method for detecting the vehicle flow of the multiple lanes on the basis of video analysis includes steps of building video background models; setting transverse main virtual detection lines, auxiliary virtual detection lines and longitudinal virtual detection lines in video backgrounds; preprocessing video; building background image models by the aid of Gaussian mixture background models and detecting vehicle targets; determining whether vehicles need to be counted or not, in other words, determining whether change of relations between the vehicle targets is available in image data of each local frame on the corresponding main virtual detection line and image data of a next frame or not, according to the background image models of front and rear frames when the moving vehicles enter the main virtual detection lines; carrying out statistics on vehicle counting according to vehicle target detection results. The transverse main virtual detection lines and the auxiliary virtual detection lines are positioned on the lanes, the longitudinal virtual detection lines are positioned at the edges of the lanes, and parallel distances from the main virtual detection lines to the auxiliary virtual detection lines are fixed.

Description

technical field [0001] The invention relates to a multi-lane traffic flow detection method based on video analysis, which belongs to the field of traffic parameter collection of intelligent traffic systems. Background technique [0002] With the substantial increase in car ownership, it is very important to make high-quality use of the existing limited traffic resources to improve the automation level of urban traffic monitoring and command. To solve this problem, the research on Intelligent Transportation System (ITS) has been mentioned to a more important position. Among them, traffic flow detection is one of the important technologies and information that intelligent transportation systems need to consider. It provides an important data source for intelligent control. As the basic part of ITS, the traffic flow detection system occupies a very important position in ITS. It provides an important basis for subsequent traffic decisions such as vehicle speed measurement, lan...

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): G08G1/065G08G1/01
CPCG08G1/0125G08G1/065
Inventor 马怀志刘真杨振燕孝飞张伟王海峰董西尚单承刚王秀贞
Owner ZAOZHUANG UNIV
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