We propose a two-stage method for detection of abnormal behaviours, such as aggression and fights in urban environment, which is applicable to operator support in surveillance applications. The proposed method is based on fusion of evidence from audio and optical sensors. In the first stage, a number of modality-specific detectors perform recognition of low-level events. Their outputs act as input to the second stage, which performs fusion and disambiguation of the first-stage detections. Experimental evaluation on scenes from the outdoor part of the PROMETHEUS database demonstrated the practical viability of the proposed approach. We report a fight detection rate of 81% when both audio and optical information are used. Reduced performance is observed when evidence from audio data is excluded from the fusion process. Finally, in the case when only evidence from one camera is used for detecting the fights, the recognition performance is poor.

Fusion of acoustic and optical sensor data for automatic fight detection in urban environments / M. Andersson, S. Ntalampiras, T. Ganchev, J. Rydell, J. Ahlberg, N. Fakotakis - In: 2010 13th International Conference on Information Fusion[s.l] : IEEE, 2010. - ISBN 9780982443811. - pp. 1-8 (( Intervento presentato al 13. convegno Conference on Information Fusion tenutosi a Edinburgh, nel 2010.

Fusion of acoustic and optical sensor data for automatic fight detection in urban environments

S. Ntalampiras;
2010

Abstract

We propose a two-stage method for detection of abnormal behaviours, such as aggression and fights in urban environment, which is applicable to operator support in surveillance applications. The proposed method is based on fusion of evidence from audio and optical sensors. In the first stage, a number of modality-specific detectors perform recognition of low-level events. Their outputs act as input to the second stage, which performs fusion and disambiguation of the first-stage detections. Experimental evaluation on scenes from the outdoor part of the PROMETHEUS database demonstrated the practical viability of the proposed approach. We report a fight detection rate of 81% when both audio and optical information are used. Reduced performance is observed when evidence from audio data is excluded from the fusion process. Finally, in the case when only evidence from one camera is used for detecting the fights, the recognition performance is poor.
Abnormal behaviour detection; Acoustic data; Hidden Markov Model; Multiple sensor fusion; Thermal imaging data; Visual data; Information Systems
Settore INF/01 - Informatica
2010
International Society of Information Fusion (ISIF)
Office of Naval Research (ONR)
ONR Global
Army Research Office (ARO)
Metron
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
05712105.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 1.57 MB
Formato Adobe PDF
1.57 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/615069
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 32
  • ???jsp.display-item.citation.isi??? ND
social impact