A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications
Abstract In a new application scenario where the millimetre‐wave radar is installed above the road for detecting traffic flow in downward looking direction, the original data of the radar includes all kinds of background noises and false targets. In order to acquire effective vehicle trajectories, a...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-05-01
|
Series: | IET Intelligent Transport Systems |
Online Access: | https://doi.org/10.1049/itr2.12052 |
id |
doaj-241d8e430427462ea1266b5eef2ba753 |
---|---|
record_format |
Article |
spelling |
doaj-241d8e430427462ea1266b5eef2ba7532021-07-14T13:20:13ZengWileyIET Intelligent Transport Systems1751-956X1751-95782021-05-0115567168210.1049/itr2.12052A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applicationsHaiqing Liu0Kunmin Teng1Laxmisha Rai2Yu Zhang3Shengli Wang4College of Transportation Shandong University of Science and Technology Qingdao ChinaCollege of Transportation Shandong University of Science and Technology Qingdao ChinaCollege of Electronic and Information Engineering Shandong University of Science and Technology Shandong ChinaCollege of Transportation Shandong University of Science and Technology Qingdao ChinaOcean Science and Engineering College Shandong University of Science and Technology Qingdao ChinaAbstract In a new application scenario where the millimetre‐wave radar is installed above the road for detecting traffic flow in downward looking direction, the original data of the radar includes all kinds of background noises and false targets. In order to acquire effective vehicle trajectories, a two‐step abnormal data processing method for millimetre‐wave radar in traffic flow detection application is proposed. In the first step, the rational range of distance, angle and speed are studied, and proper thresholds are presented for reducing the samples of which the single parameter is with the obvious abnormality. Moreover, the nearest neighbour analysis method is used to further extract vehicle trajectories based on the similarity and slope characteristics of each sample to its neighbours. Taking actual detected data as samples, the weighting coefficients, similarity threshold, average slope threshold and standard deviation threshold are calibrated for the proposed nearest neighbour analysis method. The two‐step processing method presents a higher performance in extracting effective trajectory samples, and the ratio of noise points is reduced to 4.1%, compared with 239.9% in the original data sample. The proposed method can provide an effective reference for further applications, such as driving behaviour analysis and traffic flow parameter identification.https://doi.org/10.1049/itr2.12052 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Haiqing Liu Kunmin Teng Laxmisha Rai Yu Zhang Shengli Wang |
spellingShingle |
Haiqing Liu Kunmin Teng Laxmisha Rai Yu Zhang Shengli Wang A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications IET Intelligent Transport Systems |
author_facet |
Haiqing Liu Kunmin Teng Laxmisha Rai Yu Zhang Shengli Wang |
author_sort |
Haiqing Liu |
title |
A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications |
title_short |
A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications |
title_full |
A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications |
title_fullStr |
A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications |
title_full_unstemmed |
A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications |
title_sort |
two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications |
publisher |
Wiley |
series |
IET Intelligent Transport Systems |
issn |
1751-956X 1751-9578 |
publishDate |
2021-05-01 |
description |
Abstract In a new application scenario where the millimetre‐wave radar is installed above the road for detecting traffic flow in downward looking direction, the original data of the radar includes all kinds of background noises and false targets. In order to acquire effective vehicle trajectories, a two‐step abnormal data processing method for millimetre‐wave radar in traffic flow detection application is proposed. In the first step, the rational range of distance, angle and speed are studied, and proper thresholds are presented for reducing the samples of which the single parameter is with the obvious abnormality. Moreover, the nearest neighbour analysis method is used to further extract vehicle trajectories based on the similarity and slope characteristics of each sample to its neighbours. Taking actual detected data as samples, the weighting coefficients, similarity threshold, average slope threshold and standard deviation threshold are calibrated for the proposed nearest neighbour analysis method. The two‐step processing method presents a higher performance in extracting effective trajectory samples, and the ratio of noise points is reduced to 4.1%, compared with 239.9% in the original data sample. The proposed method can provide an effective reference for further applications, such as driving behaviour analysis and traffic flow parameter identification. |
url |
https://doi.org/10.1049/itr2.12052 |
work_keys_str_mv |
AT haiqingliu atwostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT kunminteng atwostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT laxmisharai atwostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT yuzhang atwostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT shengliwang atwostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT haiqingliu twostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT kunminteng twostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT laxmisharai twostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT yuzhang twostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications AT shengliwang twostepabnormaldataanalysisandprocessingmethodformillimetrewaveradarintrafficflowdetectionapplications |
_version_ |
1721302896017932288 |