Smartphone orientation estimation algorithm combining Kalman filter with gradient descent

Availability and all-in-one functionality of smartphones have become a multipurpose personal tool to improve our daily life. Recent advancements in hardware and accessibility of smartphones have spawn huge potential for assistive healthcare, in particular telerehabilitation. However, using smartphon...

Full description

Saved in:
Bibliographic Details
Main Authors: Yean, Seanglidet, Lee, Bu Sung, Yeo, Chai Kiat, Vun, Chan Hua, Oh, Hong Lye
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/140000
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-140000
record_format dspace
spelling sg-ntu-dr.10356-1400002020-05-26T03:31:43Z Smartphone orientation estimation algorithm combining Kalman filter with gradient descent Yean, Seanglidet Lee, Bu Sung Yeo, Chai Kiat Vun, Chan Hua Oh, Hong Lye School of Computer Science and Engineering Engineering::Computer science and engineering Algorithm Sensor Fusion Availability and all-in-one functionality of smartphones have become a multipurpose personal tool to improve our daily life. Recent advancements in hardware and accessibility of smartphones have spawn huge potential for assistive healthcare, in particular telerehabilitation. However, using smartphone sensors face certain challenges, in particular, accurate orientation estimation, which is usually less of a problem in specialized motion tracking sensor devices. Drift is one of the challenges. We first propose a simple feedback loop complementary filter (CFF) to reduce the error caused by the integration of the gyroscope's data in the orientation estimation. Next, we propose a new and better orientation estimation algorithm which combines quaternion-based kalman filter with corrector estimates using gradient descent (KFGD). We then evaluate CFF's and KFGD's performance on two early-stage rehabilitation exercises. The results show that CFF is capable of fast motion tracking and confirm that the feedback loop can correct the error caused by the integration of gyroscope data. The KFGD orientation estimation is comparable to XSENS Awinda and has shown itself to be stable than and outperforms CFF. KFGD also outperforms the prominent Madgwick algorithm using mobile data. Thus, KFGD is suitable for low-cost motion sensors or mobile inertial sensors, especially during early recovery stage of sport injuries and exercise for the elderly. 2020-05-26T03:31:43Z 2020-05-26T03:31:43Z 2017 Journal Article Yean, S., Lee, B. S., Yeo, C. K., Vun, C. H., & Oh, H. L. (2018). Smartphone orientation estimation algorithm combining Kalman filter with gradient descent. IEEE Journal of Biomedical and Health Informatics, 22(5), 1421-1433. doi:10.1109/JBHI.2017.2780879 2168-2194 https://hdl.handle.net/10356/140000 10.1109/JBHI.2017.2780879 29990245 2-s2.0-85037597642 5 22 1421 1433 en IEEE Journal of Biomedical and Health Informatics © 2017 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Algorithm
Sensor Fusion
spellingShingle Engineering::Computer science and engineering
Algorithm
Sensor Fusion
Yean, Seanglidet
Lee, Bu Sung
Yeo, Chai Kiat
Vun, Chan Hua
Oh, Hong Lye
Smartphone orientation estimation algorithm combining Kalman filter with gradient descent
description Availability and all-in-one functionality of smartphones have become a multipurpose personal tool to improve our daily life. Recent advancements in hardware and accessibility of smartphones have spawn huge potential for assistive healthcare, in particular telerehabilitation. However, using smartphone sensors face certain challenges, in particular, accurate orientation estimation, which is usually less of a problem in specialized motion tracking sensor devices. Drift is one of the challenges. We first propose a simple feedback loop complementary filter (CFF) to reduce the error caused by the integration of the gyroscope's data in the orientation estimation. Next, we propose a new and better orientation estimation algorithm which combines quaternion-based kalman filter with corrector estimates using gradient descent (KFGD). We then evaluate CFF's and KFGD's performance on two early-stage rehabilitation exercises. The results show that CFF is capable of fast motion tracking and confirm that the feedback loop can correct the error caused by the integration of gyroscope data. The KFGD orientation estimation is comparable to XSENS Awinda and has shown itself to be stable than and outperforms CFF. KFGD also outperforms the prominent Madgwick algorithm using mobile data. Thus, KFGD is suitable for low-cost motion sensors or mobile inertial sensors, especially during early recovery stage of sport injuries and exercise for the elderly.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Yean, Seanglidet
Lee, Bu Sung
Yeo, Chai Kiat
Vun, Chan Hua
Oh, Hong Lye
format Article
author Yean, Seanglidet
Lee, Bu Sung
Yeo, Chai Kiat
Vun, Chan Hua
Oh, Hong Lye
author_sort Yean, Seanglidet
title Smartphone orientation estimation algorithm combining Kalman filter with gradient descent
title_short Smartphone orientation estimation algorithm combining Kalman filter with gradient descent
title_full Smartphone orientation estimation algorithm combining Kalman filter with gradient descent
title_fullStr Smartphone orientation estimation algorithm combining Kalman filter with gradient descent
title_full_unstemmed Smartphone orientation estimation algorithm combining Kalman filter with gradient descent
title_sort smartphone orientation estimation algorithm combining kalman filter with gradient descent
publishDate 2020
url https://hdl.handle.net/10356/140000
_version_ 1681057310612389888