Unlock instant, AI-driven research and patent intelligence for your innovation.

Data and information fusion method based on fixed and mobile vehicle detection data

A fixed detection and vehicle detection technology, applied in the field of traffic engineering, which can solve the problems of inaccurate calculation results and lack of micro-state consideration in traffic information processing methods.

Active Publication Date: 2020-10-30
SOUTHWEST JIAOTONG UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Kalman filter algorithm is relatively simple, but the calculation results are not precise, and the traffic information processing method involved lacks the consideration of the micro state (such as individual passing time)

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
  • Data and information fusion method based on fixed and mobile vehicle detection data
  • Data and information fusion method based on fixed and mobile vehicle detection data
  • Data and information fusion method based on fixed and mobile vehicle detection data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The main flow of the method of the present invention is as figure 1 shown.

[0061] The modeling method proposed by the present invention is to find the "most probable" matching result between the upstream and downstream stationary detection data. In order to make the model more realistic, after obtaining the multi-source detection data of the road section, it is calibrated with the historical traffic data set.

[0062] The lane selection probability is represented by equation (1), which is expressed as the probability of the vehicle in the downstream lane l, whose upstream lane is l′, wherein the uppercase symbol represents the random variable, and the lowercase symbol represents the value of the random variable;

[0063]

[0064] in:

[0065] is the number of historical data samples passing through the downstream channel l and the upstream channel l′;

[0066] is the total number of historical data samples passing through the downstream channel l.

[0067] ...

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 data and information fusion method based on fixed and mobile vehicle detection data, which includes decomposing the transportation system into several input and output subsystems, obtaining multi-source detector data of each subsystem; using Historical traffic data sets are used to calibrate the acquired data; a combination optimization model is established; based on the combination optimization model, the most likely match of upstream and downstream fixed detection data is sought, and the calibrated fixed detection data are directly matched one by one; artificial intelligence-based inspiration is used Tabu search algorithm matches uncalibrated fixed detection data one by one. The beneficial effect of the present invention is that the matching accuracy is significantly better than the matching accuracy based on a single data source, and numerical experiments show that the accuracy is increased by 15%-20%. At the same time, it can better describe individual travel conditions (such as travel time). Experiments show that the root mean square difference of individual travel times obtained by this method is 15%-21% higher than the estimation results based on average travel time.

Description

technical field [0001] The invention relates to the field of traffic engineering, in particular to a data and information fusion method based on fixed and mobile vehicle detection data. Background technique [0002] The acquisition of vehicle traffic information mainly relies on fixed detectors and mobile detectors. Although the fixed detector can detect the vehicle information more comprehensively, it can only record at fixed points, the coverage is small, the obtained data is discrete and there is a certain degree of error (such as some vehicles passing the detector but not detected); The type detector can continuously record more detailed information of vehicles, but only for vehicles equipped with this device, it cannot reflect the traffic conditions of the overall road section, and the relevant data may involve user privacy. These two types of vehicle detector data each have certain deficiencies. [0003] Traditional traffic information processing is often only aimed ...

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 Patents(China)
IPC IPC(8): G06Q10/04G06Q50/30
CPCG06Q10/04G06Q50/40
Inventor 孙湛博黄添钰
Owner SOUTHWEST JIAOTONG UNIV