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

Urban road congestion degree prediction method based on time sequence traffic events

A technology for road congestion and traffic incidents, applied in traffic flow detection, forecasting, traffic control systems, etc. Efficiency, avoidance of complex processes, effect of good applicability

Inactive Publication Date: 2019-04-30
JILIN UNIV
View PDF8 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Quantitative forecasting technology of traffic flow data is often used at home and abroad for traffic congestion problems, such as constructing linear models such as ARIMA model and Kalman filter model based on statistical theory, or constructing nonlinear models such as decision tree models and support vector machine models based on machine learning algorithms. However, due to the complexity and uncertainty of traffic flow, the time-dependent correlation of each subsystem of intelligent transportation is not strong enough, resulting in the joint realization of intelligent transportation goals by the traffic control system and guidance system.

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
  • Urban road congestion degree prediction method based on time sequence traffic events
  • Urban road congestion degree prediction method based on time sequence traffic events
  • Urban road congestion degree prediction method based on time sequence traffic events

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0049] Step 1: Obtain more than 6,000 road network data through the urban road traffic information on the public security intranet and real-time congestion information uploaded by map software users, select 82 typical urban road sections, and extract time-series traffic events 30 minutes before each road section congestion event .

[0050] Step 2: The 3D CNN architecture based on Python is as follows: figure 2 As shown, it contains a hardwired layer, 3 convolutional layers, 2 pooling layers and a fully connected layer. The cube of each 3D convolution kernel convolution takes 7 consecutive frames, each frame size is 60×40, and the information of 5 channels is extracted through the first layer, which are: grayscale, gradient in x and y directions, x and y Directional optical flow; each layer of convolution kernel u×v×3 (u×v represents the spatial dimension, 3 represents the time dimension) respectively performs convolution operations on the information of the 5 channels; using...

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 urban road congestion degree prediction method based on time sequence traffic events. The method comprises the steps of: S1, acquiring historical traffic event data, real-time traffic event data and video monitoring data of an urban road section; S2, identifying traffic congestion forewarning events in the video data through the 3D CNN, and performing data space-time fusion according to the historical traffic events; S3, determining congestion degree classification labels, constructing a time sequence traffic congestion event data dictionary, and screening a training set, a verification set and a test set; S4, establishing an LSTM sequence data classification model, inputting the training set, and iteratively updating model parameters by utilizing a gradient descent method; S5, inputting the verification set into the model with updated parameters, optimizing and adjusting hyper-parameters, and selecting an optimal model; and S6, inputting the test set into the optimal training model, checking the effectiveness of the model, and carrying out road congestion prediction according to real-time traffic monitoring data. According to the method, a sequence dataclassification model is established by using LSTM, and the urban road congestion degree is predicted based on time sequence traffic events.

Description

technical field [0001] The invention belongs to the technical field of urban intelligent traffic management, and relates to a method for predicting urban road congestion degree based on time series traffic events. Background technique [0002] At present, in order to effectively alleviate traffic congestion, reduce traffic accidents, improve road network capacity, reduce energy consumption and reduce environmental pollution, many cities have built intelligent transportation systems (ITS), the key technology of which is to be able to monitor the future traffic conditions of urban roads. Effective forecasting provides decision-making basis for urban traffic control and road guidance systems. [0003] Quantitative forecasting technology of traffic flow data is often used at home and abroad for traffic congestion problems, such as constructing linear models such as ARIMA model and Kalman filter model based on statistical theory, or constructing nonlinear models such as decision ...

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): G08G1/01G06K9/00G06N3/04G06N3/08G06Q10/04G06Q50/26
CPCG06N3/084G06Q10/04G06Q50/26G08G1/0129G06V20/47G06V20/53G06V20/41G06N3/045
Inventor 刘宏飞许淼许洪国王郭俊方杏花
Owner JILIN 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