Vehicle video recognition-based hybrid main line toll station traffic conflict evaluation method

A traffic conflict and video recognition technology, which is applied in the traffic control system of road vehicles, traffic control system, character and pattern recognition, etc., can solve problems such as hidden dangers of accidents, and achieve the effect of large storage capacity, simple calculation, fast and accurate calculation

Active Publication Date: 2017-10-13
SOUTHEAST UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although it alleviates the congestion problem at toll booths to a certain extent, it may also cause accident hazards

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
  • Vehicle video recognition-based hybrid main line toll station traffic conflict evaluation method
  • Vehicle video recognition-based hybrid main line toll station traffic conflict evaluation method
  • Vehicle video recognition-based hybrid main line toll station traffic conflict evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0044] In this embodiment, the traffic conflict problem of the toll station is analyzed by collecting a total of 3 minutes and 50 seconds of video taken at the hybrid main line toll station on the Shanghai-Hangzhou-Ningbo S2 Expressway at 8:30-8:34 in the morning.

[0045] The present invention provides a traffic conflict evaluation method for hybrid main line toll stations based on vehicle video recognition, such as figure 1 shown, including the following steps:

[0046] Step 1. Arrange a camera in the toll plaza of the toll station, and use the camera to collect the driving video of the vehicle in the toll plaza;

[0047] The number N of cameras arranged in the toll plaza is:

[0048]

[0049] Wherein m is the number of toll passages, and I is the number of toll passages that the camera can photograph, which is relevant to camera paramet...

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 vehicle video recognition-based hybrid main line toll station traffic conflict evaluation method. The method includes the following steps that: 1, cameras are arranged the toll station square of a toll station to acquire the driving video of vehicles in the toll station square; 2, vehicle identification and tracking are performed in the acquired driving video of the vehicles, the position coordinates of the vehicles in each frame of image are obtained; 3, the data of M frames of images of the vehicles are utilized to calculate the speeds V

i and deceleration indexes DR

i of the vehicles in each frame of image; if a vehicle-following conflict occurs, the time index TTCk of a vehicle-following model is calculated, and if a lane change conflict occurs, the time index Tpet of a vehicle steering model is calculated; and 5, peering processing is performed on the DR

i, TTCk and Tpet, so that the DR

i, TTCk and Tpet can be unified into traffic conflict evaluation indexes STC, and the severity degree of the traffic conflict is judged according to the values of the traffic conflict evaluation indexes STC. With the method adopted, the severity degree of the traffic conflict of the toll station can be quantified. The method has a great application value in decision making such as toll station road safety evaluation, management operation and road traffic flow guidance.

Description

technical field [0001] The invention belongs to the technical field of expressway management, and in particular relates to a traffic conflict evaluation method of a toll station. Background technique [0002] With the rapid development of China's economy in recent years, the mileage of expressways is also increasing. As the "throat" zone of the expressway, the toll station determines the traffic capacity and service level of the road section near the toll station or even the entire road section. As the traffic volume increases year by year, the traffic load borne by the toll stations on the main line is also increasing. Most of the toll stations in our country adopt the combination of non-stop automatic toll collection and parking semi-automatic toll collection. Although it alleviates the congestion problem at the toll booth to a certain extent, it may also cause accident hazards. [0003] With the development of traffic analysis technology, the theory of traffic conflict...

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): G08G1/017G06K9/00G06Q50/26
CPCG06Q50/26G08G1/0175G06V20/42
Inventor 何杰吴冠鹤刘子洋邢璐杭文周博见
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products