Improvement of Acoustic Fall Detection using Kinect Depth Sensing

Yun Li; Tanvi Banerjee; Mihail Popescu; Marjorie Skubic

doi:10.1109/EMBC.2013.6611102

Improvement of Acoustic Fall Detection using Kinect Depth Sensing

Yun Li, Tanvi Banerjee, Mihail Popescu, Marjorie Skubic

Computer Science and Engineering

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

Abstract

The latest acoustic fall detection system (acoustic FADE) has achieved encouraging results on real-world dataset. However, the acoustic FADE device is difficult to be deployed in real environment due to its large size. In addition, the estimation accuracy of sound source localization (SSL) and direction of arrival (DOA) becomes much lower in multi-interference environment, which will potentially result in the distortion of the source signal using beamforming (BF). Microsoft Kinect is used in this paper to address these issues by measuring source position using the depth sensor. We employ robust minimum variance distortionless response (MVDR) adaptive BF (ABF) to take advantage of well-estimated source position for acoustic FADE. A significant reduction of false alarms and improvement of detection rate are both achieved using the proposed fusion strategy on real-world data.

Original language	English
Title of host publication	2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Publisher	IEEE
Pages	6736-6739
Number of pages	4
ISBN (Electronic)	978-1-4577-0216-7
DOIs	https://doi.org/10.1109/EMBC.2013.6611102
State	Published - 2013
Event	2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, Japan Duration: Jul 3 2013 → Jul 7 2013

Conference

Conference	2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Country/Territory	Japan
City	Osaka
Period	7/3/13 → 7/7/13

ASJC Scopus Subject Areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

Keywords

Acoustics
Array Signal Processing
Arrays
Direction-Of-Arrival Estimation
Microphones
Noise Measurement
Sensors

Disciplines

Bioinformatics
Communication Technology and New Media
Databases and Information Systems
OS and Networks
Science and Technology Studies

Access to Document

10.1109/EMBC.2013.6611102License: Unspecified

Cite this

Li, Y, Banerjee, T, Popescu, M & Skubic, M 2013, Improvement of Acoustic Fall Detection using Kinect Depth Sensing. in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013., 6611102, IEEE, pp. 6736-6739, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013, Osaka, Japan, 7/3/13. https://doi.org/10.1109/EMBC.2013.6611102

@inproceedings{d057456703c847c2a8130cd1907097ef,

title = "Improvement of Acoustic Fall Detection using Kinect Depth Sensing",

abstract = " The latest acoustic fall detection system (acoustic FADE) has achieved encouraging results on real-world dataset. However, the acoustic FADE device is difficult to be deployed in real environment due to its large size. In addition, the estimation accuracy of sound source localization (SSL) and direction of arrival (DOA) becomes much lower in multi-interference environment, which will potentially result in the distortion of the source signal using beamforming (BF). Microsoft Kinect is used in this paper to address these issues by measuring source position using the depth sensor. We employ robust minimum variance distortionless response (MVDR) adaptive BF (ABF) to take advantage of well-estimated source position for acoustic FADE. A significant reduction of false alarms and improvement of detection rate are both achieved using the proposed fusion strategy on real-world data.",

keywords = "Acoustics, Array Signal Processing, Arrays, Direction-Of-Arrival Estimation, Microphones, Noise Measurement, Sensors",

author = "Yun Li and Tanvi Banerjee and Mihail Popescu and Marjorie Skubic",

year = "2013",

doi = "10.1109/EMBC.2013.6611102",

language = "English",

pages = "6736--6739",

booktitle = "2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013",

publisher = "IEEE",

note = "2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 ; Conference date: 03-07-2013 Through 07-07-2013",

}

TY - GEN

T1 - Improvement of Acoustic Fall Detection using Kinect Depth Sensing

AU - Li, Yun

AU - Banerjee, Tanvi

AU - Popescu, Mihail

AU - Skubic, Marjorie

PY - 2013

Y1 - 2013

N2 - The latest acoustic fall detection system (acoustic FADE) has achieved encouraging results on real-world dataset. However, the acoustic FADE device is difficult to be deployed in real environment due to its large size. In addition, the estimation accuracy of sound source localization (SSL) and direction of arrival (DOA) becomes much lower in multi-interference environment, which will potentially result in the distortion of the source signal using beamforming (BF). Microsoft Kinect is used in this paper to address these issues by measuring source position using the depth sensor. We employ robust minimum variance distortionless response (MVDR) adaptive BF (ABF) to take advantage of well-estimated source position for acoustic FADE. A significant reduction of false alarms and improvement of detection rate are both achieved using the proposed fusion strategy on real-world data.

AB - The latest acoustic fall detection system (acoustic FADE) has achieved encouraging results on real-world dataset. However, the acoustic FADE device is difficult to be deployed in real environment due to its large size. In addition, the estimation accuracy of sound source localization (SSL) and direction of arrival (DOA) becomes much lower in multi-interference environment, which will potentially result in the distortion of the source signal using beamforming (BF). Microsoft Kinect is used in this paper to address these issues by measuring source position using the depth sensor. We employ robust minimum variance distortionless response (MVDR) adaptive BF (ABF) to take advantage of well-estimated source position for acoustic FADE. A significant reduction of false alarms and improvement of detection rate are both achieved using the proposed fusion strategy on real-world data.

KW - Acoustics

KW - Array Signal Processing

KW - Arrays

KW - Direction-Of-Arrival Estimation

KW - Microphones

KW - Noise Measurement

KW - Sensors

UR - http://www.scopus.com/inward/record.url?scp=84886558917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886558917&partnerID=8YFLogxK

UR - https://corescholar.libraries.wright.edu/knoesis/1110

U2 - 10.1109/EMBC.2013.6611102

DO - 10.1109/EMBC.2013.6611102

M3 - Conference contribution

C2 - 24111289

SP - 6736

EP - 6739

BT - 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013

PB - IEEE

T2 - 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013

Y2 - 3 July 2013 through 7 July 2013

ER -

Improvement of Acoustic Fall Detection using Kinect Depth Sensing

Abstract

Conference

ASJC Scopus Subject Areas

Keywords

Disciplines

Access to Document

Other files and links

Cite this