Person Tracking by Fusing Posture Data from UAV Video and Wearable Sensors

Alisher Mukashev; Lan Da Van; Susanta Sharma; M. Farhan Tandia; Yu Chee Tseng

doi:10.1109/JSEN.2022.3218373

Person Tracking by Fusing Posture Data from UAV Video and Wearable Sensors

Alisher Mukashev^*, Lan Da Van, Susanta Sharma, M. Farhan Tandia, Yu Chee Tseng

^*Corresponding author for this work

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

5 Scopus citations

Abstract

In this article, a novel framework that fuses the posture data taken by a drone (or unmanned aerial vehicle, UAV) camera and the wearable sensors data recorded by smartwatches is proposed. The framework is designed for continuously tracking persons in a drone view by analyzing location-independent human posture features and correctly tagging smartwatch identities (IDs) and personal profiles to video human objects, thus conquering the former work in requiring ground markers. Person detection, ID assignment, and pose estimation are integrated into our framework to obtain recognized human postures. These recognized postures are then paired with those from the wearable sensors. Through fusing common postures, such as standing, walking, jumping, and falling down, person tracking accuracy by UAV up to 95.36% can be attained in our testing scenarios.

Original language	English
Pages (from-to)	24150-24160
Number of pages	11
Journal	IEEE Sensors Journal
Volume	22
Issue number	24
DOIs	https://doi.org/10.1109/JSEN.2022.3218373
State	Published - 15 Dec 2022

Keywords

Action recognition
data fusion
drone
person identification
person tracking
wearable devices

Access to Document

10.1109/JSEN.2022.3218373

Cite this

@article{c257743ef88642b484b6f10c5c5a9d50,

title = "Person Tracking by Fusing Posture Data from UAV Video and Wearable Sensors",

abstract = "In this article, a novel framework that fuses the posture data taken by a drone (or unmanned aerial vehicle, UAV) camera and the wearable sensors data recorded by smartwatches is proposed. The framework is designed for continuously tracking persons in a drone view by analyzing location-independent human posture features and correctly tagging smartwatch identities (IDs) and personal profiles to video human objects, thus conquering the former work in requiring ground markers. Person detection, ID assignment, and pose estimation are integrated into our framework to obtain recognized human postures. These recognized postures are then paired with those from the wearable sensors. Through fusing common postures, such as standing, walking, jumping, and falling down, person tracking accuracy by UAV up to 95.36% can be attained in our testing scenarios.",

keywords = "Action recognition, data fusion, drone, person identification, person tracking, wearable devices",

author = "Alisher Mukashev and Van, {Lan Da} and Susanta Sharma and Tandia, {M. Farhan} and Tseng, {Yu Chee}",

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

year = "2022",

month = dec,

day = "15",

doi = "10.1109/JSEN.2022.3218373",

language = "English",

volume = "22",

pages = "24150--24160",

journal = "IEEE Sensors Journal",

issn = "1530-437X",

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

number = "24",

}

TY - JOUR

T1 - Person Tracking by Fusing Posture Data from UAV Video and Wearable Sensors

AU - Mukashev, Alisher

AU - Van, Lan Da

AU - Sharma, Susanta

AU - Tandia, M. Farhan

AU - Tseng, Yu Chee

PY - 2022/12/15

Y1 - 2022/12/15

N2 - In this article, a novel framework that fuses the posture data taken by a drone (or unmanned aerial vehicle, UAV) camera and the wearable sensors data recorded by smartwatches is proposed. The framework is designed for continuously tracking persons in a drone view by analyzing location-independent human posture features and correctly tagging smartwatch identities (IDs) and personal profiles to video human objects, thus conquering the former work in requiring ground markers. Person detection, ID assignment, and pose estimation are integrated into our framework to obtain recognized human postures. These recognized postures are then paired with those from the wearable sensors. Through fusing common postures, such as standing, walking, jumping, and falling down, person tracking accuracy by UAV up to 95.36% can be attained in our testing scenarios.

AB - In this article, a novel framework that fuses the posture data taken by a drone (or unmanned aerial vehicle, UAV) camera and the wearable sensors data recorded by smartwatches is proposed. The framework is designed for continuously tracking persons in a drone view by analyzing location-independent human posture features and correctly tagging smartwatch identities (IDs) and personal profiles to video human objects, thus conquering the former work in requiring ground markers. Person detection, ID assignment, and pose estimation are integrated into our framework to obtain recognized human postures. These recognized postures are then paired with those from the wearable sensors. Through fusing common postures, such as standing, walking, jumping, and falling down, person tracking accuracy by UAV up to 95.36% can be attained in our testing scenarios.

KW - Action recognition

KW - data fusion

KW - drone

KW - person identification

KW - person tracking

KW - wearable devices

UR - http://www.scopus.com/inward/record.url?scp=85141567308&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2022.3218373

DO - 10.1109/JSEN.2022.3218373

M3 - Article

AN - SCOPUS:85141567308

SN - 1530-437X

VL - 22

SP - 24150

EP - 24160

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

IS - 24

ER -

Person Tracking by Fusing Posture Data from UAV Video and Wearable Sensors

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this