Selective background adaptation based abnormal acoustic event recognition for audio surveillance

Woohyun Choi, Jinsang Rho, David K. Han, Hanseok Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

In this paper, a method for abnormal acoustic event recognition in an audio surveillance system is presented. We propose a recognition scheme based on a hierarchical structure using a feature combination of Mel-Frequency Cepstral Coefficient (MFCC), timbre, and spectral statistics. A selective background adaptation is proposed for robust abnormal acoustic event recognition in real-world situations. For training, we use a database containing 9 abnormal events (scream, glass breaking, and etc.) and 6 background noise types collected under various surveillance situations. Gaussian Mixture Model (GMM) is considered for classifying the representative abnormal acoustic events and for selecting the background noise for adaptation. Effectiveness of the proposed method is demonstrated via representative experimental results.

Original languageEnglish
Title of host publicationProceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012
Pages118-123
Number of pages6
DOIs
Publication statusPublished - 2012 Nov 6
Event2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012 - Beijing, China
Duration: 2012 Sep 182012 Sep 21

Other

Other2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012
CountryChina
CityBeijing
Period12/9/1812/9/21

Fingerprint

Acoustics
Acoustic noise
Statistics
Glass

Keywords

  • Abnormal acoustic event recognition
  • Audio surveillance
  • Background adaptation

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Choi, W., Rho, J., Han, D. K., & Ko, H. (2012). Selective background adaptation based abnormal acoustic event recognition for audio surveillance. In Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012 (pp. 118-123). [6327995] https://doi.org/10.1109/AVSS.2012.65

Selective background adaptation based abnormal acoustic event recognition for audio surveillance. / Choi, Woohyun; Rho, Jinsang; Han, David K.; Ko, Hanseok.

Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012. 2012. p. 118-123 6327995.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Choi, W, Rho, J, Han, DK & Ko, H 2012, Selective background adaptation based abnormal acoustic event recognition for audio surveillance. in Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012., 6327995, pp. 118-123, 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012, Beijing, China, 12/9/18. https://doi.org/10.1109/AVSS.2012.65
Choi W, Rho J, Han DK, Ko H. Selective background adaptation based abnormal acoustic event recognition for audio surveillance. In Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012. 2012. p. 118-123. 6327995 https://doi.org/10.1109/AVSS.2012.65
Choi, Woohyun ; Rho, Jinsang ; Han, David K. ; Ko, Hanseok. / Selective background adaptation based abnormal acoustic event recognition for audio surveillance. Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012. 2012. pp. 118-123
@inproceedings{abaf6f37fbfa499e896278e0fd8dd72f,
title = "Selective background adaptation based abnormal acoustic event recognition for audio surveillance",
abstract = "In this paper, a method for abnormal acoustic event recognition in an audio surveillance system is presented. We propose a recognition scheme based on a hierarchical structure using a feature combination of Mel-Frequency Cepstral Coefficient (MFCC), timbre, and spectral statistics. A selective background adaptation is proposed for robust abnormal acoustic event recognition in real-world situations. For training, we use a database containing 9 abnormal events (scream, glass breaking, and etc.) and 6 background noise types collected under various surveillance situations. Gaussian Mixture Model (GMM) is considered for classifying the representative abnormal acoustic events and for selecting the background noise for adaptation. Effectiveness of the proposed method is demonstrated via representative experimental results.",
keywords = "Abnormal acoustic event recognition, Audio surveillance, Background adaptation",
author = "Woohyun Choi and Jinsang Rho and Han, {David K.} and Hanseok Ko",
year = "2012",
month = "11",
day = "6",
doi = "10.1109/AVSS.2012.65",
language = "English",
isbn = "9780769547978",
pages = "118--123",
booktitle = "Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012",

}

TY - GEN

T1 - Selective background adaptation based abnormal acoustic event recognition for audio surveillance

AU - Choi, Woohyun

AU - Rho, Jinsang

AU - Han, David K.

AU - Ko, Hanseok

PY - 2012/11/6

Y1 - 2012/11/6

N2 - In this paper, a method for abnormal acoustic event recognition in an audio surveillance system is presented. We propose a recognition scheme based on a hierarchical structure using a feature combination of Mel-Frequency Cepstral Coefficient (MFCC), timbre, and spectral statistics. A selective background adaptation is proposed for robust abnormal acoustic event recognition in real-world situations. For training, we use a database containing 9 abnormal events (scream, glass breaking, and etc.) and 6 background noise types collected under various surveillance situations. Gaussian Mixture Model (GMM) is considered for classifying the representative abnormal acoustic events and for selecting the background noise for adaptation. Effectiveness of the proposed method is demonstrated via representative experimental results.

AB - In this paper, a method for abnormal acoustic event recognition in an audio surveillance system is presented. We propose a recognition scheme based on a hierarchical structure using a feature combination of Mel-Frequency Cepstral Coefficient (MFCC), timbre, and spectral statistics. A selective background adaptation is proposed for robust abnormal acoustic event recognition in real-world situations. For training, we use a database containing 9 abnormal events (scream, glass breaking, and etc.) and 6 background noise types collected under various surveillance situations. Gaussian Mixture Model (GMM) is considered for classifying the representative abnormal acoustic events and for selecting the background noise for adaptation. Effectiveness of the proposed method is demonstrated via representative experimental results.

KW - Abnormal acoustic event recognition

KW - Audio surveillance

KW - Background adaptation

UR - http://www.scopus.com/inward/record.url?scp=84868230248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868230248&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2012.65

DO - 10.1109/AVSS.2012.65

M3 - Conference contribution

AN - SCOPUS:84868230248

SN - 9780769547978

SP - 118

EP - 123

BT - Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012

ER -