Attitude Adaptive Estimation with Smartphone Classification for Pedestrian Navigation

Eran Vertzberger; Itzik Klein

doi:10.1109/jsen.2021.3053843

Attitude Adaptive Estimation with Smartphone Classification for Pedestrian Navigation

Research output: Contribution to journal › Article › peer-review

Abstract

Accurate attitude for wearable devices and smartphones is needed for many applications. The major challenge is to cope with the acceleration resulting from the user or smartphone dynamics. To that end, a two-stage adaptive complementary filter for attitude estimation is proposed. Upon identifying the smartphone location on the user using a deep learning approach, the accelerometers weights in each axis are adjusted according to an optimized gain map. To evaluate the benefits of the proposed approach it is compared to commonly used algorithms both in simulation and experiments.

Original language	English
Article number	9333630
Pages (from-to)	9341-9348
Number of pages	8
Journal	IEEE Sensors Journal
Volume	21
Issue number	7
DOIs	https://doi.org/10.1109/jsen.2021.3053843
State	Published - 1 Apr 2021

Bibliographical note

Publisher Copyright:
© 2001-2012 IEEE.

Keywords

Attitude and heading reference system
complementary filter
deep learning
inertial sensors
optimization

ASJC Scopus subject areas

Instrumentation
Electrical and Electronic Engineering

Access to Document

10.1109/jsen.2021.3053843

Cite this

@article{65390156f02b445e82660dac57da7cf0,

title = "Attitude Adaptive Estimation with Smartphone Classification for Pedestrian Navigation",

abstract = "Accurate attitude for wearable devices and smartphones is needed for many applications. The major challenge is to cope with the acceleration resulting from the user or smartphone dynamics. To that end, a two-stage adaptive complementary filter for attitude estimation is proposed. Upon identifying the smartphone location on the user using a deep learning approach, the accelerometers weights in each axis are adjusted according to an optimized gain map. To evaluate the benefits of the proposed approach it is compared to commonly used algorithms both in simulation and experiments.",

keywords = "Attitude and heading reference system, complementary filter, deep learning, inertial sensors, optimization",

author = "Eran Vertzberger and Itzik Klein",

note = "Publisher Copyright: {\textcopyright} 2001-2012 IEEE.",

year = "2021",

month = apr,

day = "1",

doi = "10.1109/jsen.2021.3053843",

language = "English",

volume = "21",

pages = "9341--9348",

journal = "IEEE Sensors Journal",

issn = "1530-437X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "7",

}

TY - JOUR

T1 - Attitude Adaptive Estimation with Smartphone Classification for Pedestrian Navigation

AU - Vertzberger, Eran

AU - Klein, Itzik

PY - 2021/4/1

Y1 - 2021/4/1

N2 - Accurate attitude for wearable devices and smartphones is needed for many applications. The major challenge is to cope with the acceleration resulting from the user or smartphone dynamics. To that end, a two-stage adaptive complementary filter for attitude estimation is proposed. Upon identifying the smartphone location on the user using a deep learning approach, the accelerometers weights in each axis are adjusted according to an optimized gain map. To evaluate the benefits of the proposed approach it is compared to commonly used algorithms both in simulation and experiments.

AB - Accurate attitude for wearable devices and smartphones is needed for many applications. The major challenge is to cope with the acceleration resulting from the user or smartphone dynamics. To that end, a two-stage adaptive complementary filter for attitude estimation is proposed. Upon identifying the smartphone location on the user using a deep learning approach, the accelerometers weights in each axis are adjusted according to an optimized gain map. To evaluate the benefits of the proposed approach it is compared to commonly used algorithms both in simulation and experiments.

KW - Attitude and heading reference system

KW - complementary filter

KW - deep learning

KW - inertial sensors

KW - optimization

UR - http://www.scopus.com/inward/record.url?scp=85100463777&partnerID=8YFLogxK

U2 - 10.1109/jsen.2021.3053843

DO - 10.1109/jsen.2021.3053843

M3 - Article

AN - SCOPUS:85100463777

SN - 1530-437X

VL - 21

SP - 9341

EP - 9348

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

IS - 7

M1 - 9333630

ER -

Attitude Adaptive Estimation with Smartphone Classification for Pedestrian Navigation

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this