Unsupervised Abnormal Crowd Activity Detection in Surveillance Systems

Łukasz Kamiński; Paweł Gardziński; Krzysztof Kowalak; Sławomir Maćkowiak

doi:10.1109/IWSSIP.2016.7502705

Scientific Information System of the Poznań University of Technology

PL EN

Main page / Publications / Unsupervised Abnormal Crowd Activity Detection in Surveillance Systems

Submit a comment

Chapter

Download BibTeX

Title

Unsupervised Abnormal Crowd Activity Detection in Surveillance Systems

Authors

Łukasz Kamiński (WEiT) ^{[ 1 ][ D ]}
Paweł Gardziński (WEiT) ^{[ 1 ][ D ]}
Krzysztof Kowalak (WEiT) ^{[ 1 ][ D ]}
Sławomir Maćkowiak (WEiT) ^{[ 2 ][ P ]}

^{[ 1 ]} Wydział Elektroniki i Telekomunikacji, Politechnika Poznańska | ^{[ 2 ]} Katedra Telekomunikacji Multimedialnej i Mikroelektroniki, Wydział Elektroniki i Telekomunikacji, Politechnika Poznańska | ^{[ D ]} phd student | ^{[ P ]} employee

Year of publication

2016

Chapter type

paper

Publication language

english

Keywords

EN

particle filter
unsupervised anomaly detection
UMN

Abstract

EN We propose an unsupervised method for abnormal crowd activity detection in surveillance systems. Proposed solution is using MPEG-7 Motion Activity descriptors and Particle Filter algorithm for classification. The experiments were performed on UMN dataset sequences. The detection results are comparable to results obtained by supervised methods.

Pages (from - to)

65 - 68

DOI

10.1109/IWSSIP.2016.7502705

URL

https://ieeexplore.ieee.org/document/7502705

Book

23rd International Conference on Systems, Signals and Image Processing (IWSSIP), Bratislava, 23-25 May, 2016

Presented on

23rd International Conference on Systems, Signals and Image Processing, IWSSIP 2016, 23-25.05.2016, Bratislava, Slovakia

Publication indexed in

WoS (15)

System created by Poznań University of Technology and Poznan Supercomputing and Networking Center

Log in through eKonto to add to SIS