Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones

Peize Li; Chris Xiaoxuan Lu

doi:10.1145/3485730.3494116

Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Motion tracklets are the basic fragments of the track followed by a moving object and constitute various everyday motion behavior. An accurate estimation of motion tracklets in 3-D space can enable a wide range of applications, ranging from human computer interaction to medical rehabilitation. This paper presents a novel dataset for accurate 6-DoF motion tracklet estimation with the inertial sensors on commodity smartphones. The dataset consists of around 100 minutes of handheld motion with 3 predominant types of motion track-lets and accurate ground truth using the Vicon systems. With the presented dataset, we further benchmarked the trajectory estimation using a lightweight neural odometry model, showcasing how the dataset can be used while providing quantitative performance for downstream tasks. Our dataset, toolkit and source code available at https://github.com/MAPS-Lab/smartphone-tracking-dataset.

Original language	English
Title of host publication	Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery, Inc
Pages	542–545
Number of pages	4
ISBN (Electronic)	9781450390972
DOIs	https://doi.org/10.1145/3485730.3494116
Publication status	Published - 15 Nov 2021
Event	19th ACM Conference on Embedded Networked Sensor Systems 2021 - Coimbra, Portugal Duration: 15 Nov 2021 → 17 Nov 2021 Conference number: 19 https://sensys.acm.org/2021/

Publication series

Name	SenSys '21
Publisher	Association for Computing Machinery

Conference

Conference	19th ACM Conference on Embedded Networked Sensor Systems 2021
Abbreviated title	SenSys 2021
Country/Territory	Portugal
City	Coimbra
Period	15/11/21 → 17/11/21
Internet address	https://sensys.acm.org/2021/

Keywords

people-centric sensing
smartphone
neural inertial tracking

Access to Document

10.1145/3485730.3494116Licence: All Rights Reserved

Motion Tracklet_LI_DOA08092021_AFVAccepted author manuscript, 3.79 MBLicence: All Rights Reserved

https://dl.acm.org/doi/abs/10.1145/3485730.3494116Licence: All Rights Reserved

Cite this

@inproceedings{ebbc24dcbecf4d48884765291fdbb1bf,

title = "Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones",

abstract = "Motion tracklets are the basic fragments of the track followed by a moving object and constitute various everyday motion behavior. An accurate estimation of motion tracklets in 3-D space can enable a wide range of applications, ranging from human computer interaction to medical rehabilitation. This paper presents a novel dataset for accurate 6-DoF motion tracklet estimation with the inertial sensors on commodity smartphones. The dataset consists of around 100 minutes of handheld motion with 3 predominant types of motion track-lets and accurate ground truth using the Vicon systems. With the presented dataset, we further benchmarked the trajectory estimation using a lightweight neural odometry model, showcasing how the dataset can be used while providing quantitative performance for downstream tasks. Our dataset, toolkit and source code available at https://github.com/MAPS-Lab/smartphone-tracking-dataset.",

keywords = "people-centric sensing, smartphone, neural inertial tracking",

author = "Peize Li and Lu, {Chris Xiaoxuan}",

year = "2021",

month = nov,

day = "15",

doi = "10.1145/3485730.3494116",

language = "English",

series = "SenSys '21",

publisher = "Association for Computing Machinery, Inc",

pages = "542–545",

booktitle = "Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems",

note = "19th ACM Conference on Embedded Networked Sensor Systems 2021, SenSys 2021 ; Conference date: 15-11-2021 Through 17-11-2021",

url = "https://sensys.acm.org/2021/",

}

Li, P & Lu, CX 2021, Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones. in Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems. SenSys '21, Association for Computing Machinery, Inc, New York, NY, USA, pp. 542–545, 19th ACM Conference on Embedded Networked Sensor Systems 2021, Coimbra, Portugal, 15/11/21. https://doi.org/10.1145/3485730.3494116

Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones. / Li, Peize; Lu, Chris Xiaoxuan.

Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems. New York, NY, USA : Association for Computing Machinery, Inc, 2021. p. 542–545 (SenSys '21).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones

AU - Li, Peize

AU - Lu, Chris Xiaoxuan

N1 - Conference code: 19

PY - 2021/11/15

Y1 - 2021/11/15

N2 - Motion tracklets are the basic fragments of the track followed by a moving object and constitute various everyday motion behavior. An accurate estimation of motion tracklets in 3-D space can enable a wide range of applications, ranging from human computer interaction to medical rehabilitation. This paper presents a novel dataset for accurate 6-DoF motion tracklet estimation with the inertial sensors on commodity smartphones. The dataset consists of around 100 minutes of handheld motion with 3 predominant types of motion track-lets and accurate ground truth using the Vicon systems. With the presented dataset, we further benchmarked the trajectory estimation using a lightweight neural odometry model, showcasing how the dataset can be used while providing quantitative performance for downstream tasks. Our dataset, toolkit and source code available at https://github.com/MAPS-Lab/smartphone-tracking-dataset.

AB - Motion tracklets are the basic fragments of the track followed by a moving object and constitute various everyday motion behavior. An accurate estimation of motion tracklets in 3-D space can enable a wide range of applications, ranging from human computer interaction to medical rehabilitation. This paper presents a novel dataset for accurate 6-DoF motion tracklet estimation with the inertial sensors on commodity smartphones. The dataset consists of around 100 minutes of handheld motion with 3 predominant types of motion track-lets and accurate ground truth using the Vicon systems. With the presented dataset, we further benchmarked the trajectory estimation using a lightweight neural odometry model, showcasing how the dataset can be used while providing quantitative performance for downstream tasks. Our dataset, toolkit and source code available at https://github.com/MAPS-Lab/smartphone-tracking-dataset.

KW - people-centric sensing

KW - smartphone

KW - neural inertial tracking

U2 - 10.1145/3485730.3494116

DO - 10.1145/3485730.3494116

M3 - Conference contribution

T3 - SenSys '21

SP - 542

EP - 545

BT - Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems

PB - Association for Computing Machinery, Inc

CY - New York, NY, USA

T2 - 19th ACM Conference on Embedded Networked Sensor Systems 2021

Y2 - 15 November 2021 through 17 November 2021

ER -

Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this