OPERAnet, a multimodal activity recognition dataset acquired from radio frequency and vision-based sensors

TY - JOUR

T1 - OPERAnet, a multimodal activity recognition dataset acquired from radio frequency and vision-based sensors

AU - Bocus, Mohammud J.

AU - Li, Wenda

AU - Vishwakarma, Shelly

AU - Kou, Roget

AU - Tang, Chong

AU - Woodbridge, Karl

AU - Craddock, Ian

AU - McConville, Ryan

AU - Santos-Rodriguez, Raul

AU - Chetty, Kevin

AU - Piechocki, Robert

N1 - Copyright: © The Author(s) 2022.

PY - 2022/12

Y1 - 2022/12

N2 - This paper presents a comprehensive dataset intended to evaluate passive Human Activity Recognition (HAR) and localization techniques with measurements obtained from synchronized Radio-Frequency (RF) devices and vision-based sensors. The dataset consists of RF data including Channel State Information (CSI) extracted from a WiFi Network Interface Card (NIC), Passive WiFi Radar (PWR) built upon a Software Defined Radio (SDR) platform, and Ultra-Wideband (UWB) signals acquired via commercial off-the-shelf hardware. It also consists of vision/Infra-red based data acquired from Kinect sensors. Approximately 8 hours of annotated measurements are provided, which are collected across two rooms from 6 participants performing 6 daily activities. This dataset can be exploited to advance WiFi and vision-based HAR, for example, using pattern recognition, skeletal representation, deep learning algorithms or other novel approaches to accurately recognize human activities. Furthermore, it can potentially be used to passively track a human in an indoor environment. Such datasets are key tools required for the development of new algorithms and methods in the context of smart homes, elderly care, and surveillance applications.

AB - This paper presents a comprehensive dataset intended to evaluate passive Human Activity Recognition (HAR) and localization techniques with measurements obtained from synchronized Radio-Frequency (RF) devices and vision-based sensors. The dataset consists of RF data including Channel State Information (CSI) extracted from a WiFi Network Interface Card (NIC), Passive WiFi Radar (PWR) built upon a Software Defined Radio (SDR) platform, and Ultra-Wideband (UWB) signals acquired via commercial off-the-shelf hardware. It also consists of vision/Infra-red based data acquired from Kinect sensors. Approximately 8 hours of annotated measurements are provided, which are collected across two rooms from 6 participants performing 6 daily activities. This dataset can be exploited to advance WiFi and vision-based HAR, for example, using pattern recognition, skeletal representation, deep learning algorithms or other novel approaches to accurately recognize human activities. Furthermore, it can potentially be used to passively track a human in an indoor environment. Such datasets are key tools required for the development of new algorithms and methods in the context of smart homes, elderly care, and surveillance applications.

KW - Computer science

KW - Electrical and electronic engineering

U2 - 10.1038/s41597-022-01573-2

DO - 10.1038/s41597-022-01573-2

M3 - Article

C2 - 35922418

SN - 2052-4436

VL - 9

JO - Scientific Data

JF - Scientific Data

M1 - 474

ER -