Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multi-source traffic data complementing method based on low rank

A traffic data, low-rank technology, applied in the field of multi-source traffic data completion, can solve the problems of traffic data data loss, difficulty in adding information to models, restricting analysis performance, etc., to achieve the effect of improving accuracy

Active Publication Date: 2016-06-15
BEIJING UNIV OF TECH
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method has achieved very good experimental results, its research object is only the time correlation of a single detector for data, and does not consider the spatial correlation between road networks constructed by multiple detectors.
On the other hand, direct low-rank constraints on the reconstructed samples make it difficult for us to add more information to the model according to the characteristics of the samples
[0005] Due to the hardware failure or communication failure of the acquisition equipment, the observed traffic data often have different degrees of data loss or noise.
These missing traffic data often severely restrict the analytical performance of ITS

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
  • Multi-source traffic data complementing method based on low rank
  • Multi-source traffic data complementing method based on low rank
  • Multi-source traffic data complementing method based on low rank

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Such as figure 2 As shown, the completion method based on low-rank multi-source traffic data, the method includes the following steps:

[0021] (1) Construct a data matrix from multi-source traffic data;

[0022] (2) Calculate the low-rank representation of each traffic data matrix separately;

[0023] (3) Constrain the low-rank representations of each matrix to be similar to each other.

[0024] The present invention applies the low-rank representation model to the traffic data complement. Different from the traditional single-type traffic data complement method, the present invention combines multiple types of traffic data (multi-source traffic data) to complement the missing data. Integrating, and introducing a representation learning model to mine the internal structure of multi-source traffic data and constrain its similarity, so that the accuracy of completion is greatly improved when the loss rate is large.

[0025] Preferably, in the step (2): calculate the ...

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 multi-source traffic data complementing method based on a low rank, and the method can enable the precision of the complemented data to be greatly improved during data loss. The method comprises the steps: (1), constructing data matrixes from the multi-source traffic data; (2), respectively calculating the low-rank expression of each type of traffic data matrix; (3), enabling the low-rank expressions of all traffic data matrixes to be similar to each other through constraint.

Description

technical field [0001] The invention belongs to the technical field of image processing and intelligent transportation, and in particular relates to a complement method based on low-rank multi-source traffic data. Background technique [0002] In recent years, with the continuous advancement of the urbanization process, the speed of urban road network construction has been unable to meet the demand for the surge in urban car ownership, and traffic congestion has become increasingly serious. However, due to environmental and economic reasons, it is difficult for people to solve the problem of urban traffic congestion by simply building or widening roads. Therefore, how to optimize the existing traffic network and guide people's travel routes has played an increasingly critical role in controlling traffic congestion. Currently, Intelligent Transportation Systems (ITS) play an important role in optimizing the traffic network. In order to be able to analyze and avoid traffic j...

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): G08G1/01
CPCG08G1/0125
Inventor 孙艳丰杜蓉张勇刘浩王博岳
Owner BEIJING UNIV OF TECH
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
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