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

Intersection traffic conflict discrimination method based on real-time vehicle track

A technology of traffic conflicts and vehicle trajectories, applied in the field of traffic engineering, can solve problems such as inaccurate target detection and poor tracking effect

Active Publication Date: 2020-07-24
HEILONGJIANG INST OF TECH
View PDF11 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still many problems in the existing research on the use of video technology to detect traffic conflicts, such as inaccurate target detection, poor tracking effect, 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
  • Intersection traffic conflict discrimination method based on real-time vehicle track
  • Intersection traffic conflict discrimination method based on real-time vehicle track
  • Intersection traffic conflict discrimination method based on real-time vehicle track

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] This embodiment relates to the specific process of a method for judging traffic conflicts at intersections based on real-time vehicle trajectories, such as figure 1 Shown:

[0078] Step 1, collecting real-time video image data, and performing image grayscale, median filtering and binarization preprocessing on it;

[0079] Step 2. Establish a video background model according to the mixed Gaussian background model, and extract vehicle targets through morphological filtering;

[0080] Step 3, according to the centroid coordinates of the minimum circumscribed rectangular frame of the extended Kalman filter method, the running track of the vehicle is obtained, and the moving target is tracked;

[0081] Step 4, collecting traffic flow trajectory velocity parameter data at the intersection;

[0082] Step 5. Based on the real-time traffic flow data, create a vehicle traffic conflict discrimination model and a conflict counting method.

Embodiment 2

[0084] combine figure 2 To illustrate this embodiment, take the intersection of Songshan Road and Huaihe Road in Harbin City as an example. Right-turning vehicles at this intersection are not subject to signal restrictions, so there may be traffic conflicts between straight-going and right-turning vehicles.

[0085] In this embodiment, the specific process of preprocessing the image grayscale, median filter and binarization in the above steps is as follows:

[0086] (1) Using the moving average method to grayscale the video image, the formula for converting color pixels to grayscale pixels is:

[0087] GRAY=0.299R+0.587G+0.114B

[0088] In the formula, R, G, B——the red, green, and blue components of the original image;

[0089] For images before and after processing, see Figure 3a and 3b .

[0090] (2) Perform median filtering and denoising processing on the grayscaled image, see Figure 3c , the formula of the two-dimensional median filter is as follows:

[0091] g(x...

Embodiment 3

[0103] combine figure 2 and Figure 4 To illustrate this embodiment, in this embodiment, the above step 2 establishes a video background model according to the mixed Gaussian background model, and the specific process of extracting the vehicle target through morphological filtering is as follows:

[0104] (1) Use the mixed Gaussian distribution model to establish the background model of the video, and perform background difference to extract the vehicle image. The steps are as follows:

[0105] Step A, initializing K groups of Gaussian models;

[0106] The pixel X in the current frame is differentiated from K models respectively. If the difference result of the i-th group is less than the threshold value (generally 2.5σ), it is called pixel X t , matches with the i-th group of Gaussian models, otherwise it is called mismatch;

[0107] Step B, update the weight, the update formula is:

[0108] ω i,t =(1-a)ω i,t-1 +M i,t a

[0109] where a is the update rate, when the p...

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 an intersection traffic conflict discrimination method based on a real-time vehicle track. The method comprises the following steps: 1, collecting real-time video image data,and carrying out image graying, median filtering and binarization preprocessing; 2, establishing a video background model according to a Gaussian mixture background model, and extracting a vehicle target through morphological filtering; 3, according to the centroid coordinates of a minimum external rectangular frame of an extended Kalman filtering method, obtaining the moving track of a vehicle, and tracking a moving target; 4, acquiring intersection traffic flow track speed parameter data; and 5, based on the real-time traffic flow data, creating a traffic conflict discrimination model and aconflict counting method of the vehicle. The invention provides a video-based traffic conflict discrimination and counting method for vehicle moving tracks, traffic conflicts at intersections can be detected in real time and counted, higher efficiency and more accuracy are achieved, and compared with the traffic conflict number obtained by a manual counting method, the accuracy is higher.

Description

technical field [0001] The invention belongs to the field of traffic engineering, in particular to a method for judging traffic conflicts at intersections based on real-time vehicle trajectories. Background technique [0002] As an important part of the road system, level intersections have many traffic safety risks due to large traffic volume, many conflict points, large blind spots, and the gathering point of traffic flow in all directions. At present, the collection method of traffic conflicts is mainly through manual observation, which is poor in real-time and time-consuming and laborious, and the collected information is not accurate enough. With the development of intelligent transportation technology, it is possible to use video detection technology to discriminate and count traffic conflicts. However, there are still many problems in the existing research on traffic conflict detection system using video technology, such as inaccurate target detection and poor tracki...

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): G08G1/01G06T7/20G06T7/136
CPCG06T7/20G06T2207/10016G06T2207/20032G06T2207/30236G06T2207/30241G06T2207/30248G08G1/0104G08G1/0125G06T7/136
Inventor 吴丽娜慈玉生尹必清韩应轩吴海龙
Owner HEILONGJIANG INST OF TECH
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