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

Intelligent flow identification and statistics method for complex traffic intersection

A traffic intersection and flow recognition technology, applied in the field of intelligent transportation, can solve the problems that the traffic statistics cannot reach the expected goal, few vehicles turn to statistics, and cannot be applied.

Active Publication Date: 2020-08-18
ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY +1
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The difficulty of solving the above problems and defects is: in the previous technology, due to the limitation of computer computing power, it is often impossible to use the target detection algorithm based on deep learning with higher detection accuracy, so the previous technology often fails to meet expectations in terms of traffic statistics The goal
On the other hand, due to the lack of application of road division-related technologies in traffic flow statistics, many methods for counting vehicles can only be applied to straight roads, but cannot be applied to other complex traffic intersections such as T-junctions and crossroads. There are related technologies to achieve vehicle steering statistics at complex traffic intersections

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
  • Intelligent flow identification and statistics method for complex traffic intersection
  • Intelligent flow identification and statistics method for complex traffic intersection
  • Intelligent flow identification and statistics method for complex traffic intersection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0144] The purpose of the present invention is to provide a method based on deep learning that can complete traffic flow statistics at complex traffic intersections. It can be applied to a variety of complex traffic intersections such as straight roads, T-junctions, and intersections. It can count the number of cars turning to other intersections at different intersections within a specified time period and identify vehicle types. It has the advantages of accurate statistical results and good real-time performance. Including the following steps:

[0145] Step 1: Make a data set and use the data set to train the YOLO_V3 detection model. Select pictures containing at least one of the following categories from the COCO2017 detection training set, including car, bus, motorbike and truck. At the same time, the label information of other categories is removed from the label set corresponding to the selected pictures above, and only the above four categories of labels are retained. ...

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 belongs to the technical field of intelligent traffic, and discloses an intelligent flow identification and statistics method for a complex traffic intersection, and the method comprisesthe steps: constructing a complex traffic intersection video data set, and training a depth detection model; automatically dividing the intersection into detection areas through mouse point selection, and numbering the detection areas; detecting a vehicle in the video picture by using the trained deep learning model; predicting the position of the next frame of the vehicle by using a target tracking algorithm according to the detected vehicle and the tracking vehicle of the previous frame; counting the traffic flow according to the change condition of the number of the intersection where thevehicle is located; and repeating the step 3 to the step 5 until the video is ended or manually stopped. According to the method, the vehicle types can be automatically recognized in various complex traffic intersection environments, the number is counted according to the vehicle types, the traffic flow between different intersections is counted, and the method has the advantages of being accuratein statistical result and good in real-time performance and has high engineering practical value.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, and in particular relates to an intelligent traffic identification and statistical method for complex traffic intersections. Background technique [0002] At present, with the continuous development of social economy, in order to meet the needs of people's daily travel, the demand for cars is expanding year by year. Coupled with the scarcity of land resources in modern cities, every inch of land is expensive, and traffic jams continue to appear and become more common and serious. Especially in the peak hours of commuting, road congestion is even more serious. This has seriously affected people's life and work efficiency in modern society, and has become a social problem that cannot be ignored and urgently needs to be improved or solved. The concept of urban brain, smart transportation and big data has given us the hope of effectively solving the problem of traffic congestion....

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): G08G1/065G06N3/04G06K9/62G06K9/00
CPCG08G1/065G06V20/54G06V2201/08G06N3/045G06F18/214
Inventor 钱亚冠马丹峰关晓惠陶祥兴李蔚楼琼潘俊云本胜
Owner ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
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