Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update

Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update

In the field of pedestrian dead reckoning (PDR), the zero velocity update (ZUPT) method with an inertial measurement unit (IMU) is a mature technology to calibrate dead reckoning. However, due to the complex walking modes of different individuals, it is essential and challenging to determine the ZUP...

Full description

Bibliographic Details
Main Authors: Ran Wei, Hongda Xu, Mingkun Yang, Xinguo Yu, Zhuoling Xiao, Bo Yan
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Sensors
Subjects:
zero velocity update
CNN
PYNQ
pedestrian dead reckoning
real-time terminal
Online Access:https://www.mdpi.com/1424-8220/21/11/3808
id doaj-0545254d39a64b99aef40feed1e90290
record_format Article
spelling doaj-0545254d39a64b99aef40feed1e902902021-06-01T01:44:59ZengMDPI AGSensors1424-82202021-05-01213808380810.3390/s21113808Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity UpdateRan Wei0Hongda Xu1Mingkun Yang2Xinguo Yu3Zhuoling Xiao4Bo Yan5School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaIn the field of pedestrian dead reckoning (PDR), the zero velocity update (ZUPT) method with an inertial measurement unit (IMU) is a mature technology to calibrate dead reckoning. However, due to the complex walking modes of different individuals, it is essential and challenging to determine the ZUPT conditions, which has a direct and significant influence on the tracking accuracy. In this research, we adopted an adaptive zero velocity update (AZUPT) method based on convolution neural networks to classify the ZUPT conditions. The AZUPT model was robust regardless of the different motion types of various individuals. AZUPT was then implemented on the Zynq-7000 SoC platform to work in real time to validate its computational efficiency and performance superiority. Extensive real-world experiments were conducted by 60 different individuals in three different scenarios. It was demonstrated that the proposed system could work equally well in different environments, making it portable for PDR to be widely performed in various real-world situations.https://www.mdpi.com/1424-8220/21/11/3808zero velocity updateCNNPYNQpedestrian dead reckoningreal-time terminal
collection DOAJ
language English
format Article
sources DOAJ
author Ran Wei
Hongda Xu
Mingkun Yang
Xinguo Yu
Zhuoling Xiao
Bo Yan
spellingShingle Ran Wei
Hongda Xu
Mingkun Yang
Xinguo Yu
Zhuoling Xiao
Bo Yan
Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update
Sensors
zero velocity update
CNN
PYNQ
pedestrian dead reckoning
real-time terminal
author_facet Ran Wei
Hongda Xu
Mingkun Yang
Xinguo Yu
Zhuoling Xiao
Bo Yan
author_sort Ran Wei
title Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update
title_short Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update
title_full Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update
title_fullStr Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update
title_full_unstemmed Real-Time Pedestrian Tracking Terminal Based on Adaptive Zero Velocity Update
title_sort real-time pedestrian tracking terminal based on adaptive zero velocity update
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2021-05-01
description In the field of pedestrian dead reckoning (PDR), the zero velocity update (ZUPT) method with an inertial measurement unit (IMU) is a mature technology to calibrate dead reckoning. However, due to the complex walking modes of different individuals, it is essential and challenging to determine the ZUPT conditions, which has a direct and significant influence on the tracking accuracy. In this research, we adopted an adaptive zero velocity update (AZUPT) method based on convolution neural networks to classify the ZUPT conditions. The AZUPT model was robust regardless of the different motion types of various individuals. AZUPT was then implemented on the Zynq-7000 SoC platform to work in real time to validate its computational efficiency and performance superiority. Extensive real-world experiments were conducted by 60 different individuals in three different scenarios. It was demonstrated that the proposed system could work equally well in different environments, making it portable for PDR to be widely performed in various real-world situations.
topic zero velocity update
CNN
PYNQ
pedestrian dead reckoning
real-time terminal
url https://www.mdpi.com/1424-8220/21/11/3808
work_keys_str_mv AT ranwei realtimepedestriantrackingterminalbasedonadaptivezerovelocityupdate
AT hongdaxu realtimepedestriantrackingterminalbasedonadaptivezerovelocityupdate
AT mingkunyang realtimepedestriantrackingterminalbasedonadaptivezerovelocityupdate
AT xinguoyu realtimepedestriantrackingterminalbasedonadaptivezerovelocityupdate
AT zhuolingxiao realtimepedestriantrackingterminalbasedonadaptivezerovelocityupdate
AT boyan realtimepedestriantrackingterminalbasedonadaptivezerovelocityupdate
_version_ 1721411643799240704

Similar Items