Fast detection of abnormal events in videos with binary features

Roberto Leyva; Victor Sanchez; Chang Tsun Li

doi:10.1109/ICASSP.2018.8461759

Fast detection of abnormal events in videos with binary features

Roberto Leyva, Victor Sanchez, Chang Tsun Li

University of Warwick

Research output: Book chapter/Published conference paper › Conference paper › peer-review

9 Citations (Scopus)

Abstract

Millions of surveillance cameras are currently installed in public places around the world, making it necessary to intelligently analyse the acquired data to detect the occurrence of abnormal events. A vast number of methods to detect such events have been recently proposed; unfortunately, there is a lack of methods capable of detecting these events as frames are acquired, also known as online processing. In this paper, we present an online framework for video anomaly detection that employs binary features to encode motion information, and low-complexity probabilistic models for detection. Evaluation results on the popular UCSD dataset and on a recently introduced real-event video surveillance dataset show that our framework outperforms non-online and online methods.

Original language	English
Title of host publication	2018 IEEE International conference on acoustics, speech, and signal processing (ICASSP)
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1318-1322
Number of pages	5
Edition	April 2018
ISBN (Electronic)	9781538646588
ISBN (Print)	9781538646588
DOIs	https://doi.org/10.1109/ICASSP.2018.8461759
Publication status	Published - 13 Sept 2018
Event	2018 IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2018 - Calgary Telus Convention Center, Calgary, Canada Duration: 15 Apr 2018 → 20 Apr 2018 https://2018.ieeeicassp.org/ (Conference website)

Conference

Conference	2018 IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	Signal processing and artificial intelligence: Changing the world
Country/Territory	Canada
City	Calgary
Period	15/04/18 → 20/04/18
Internet address	https://2018.ieeeicassp.org/ (Conference website)

Access to Document

10.1109/ICASSP.2018.8461759

Cite this

@inproceedings{5e9fab9af0d24b499b34f6da74211c96,

title = "Fast detection of abnormal events in videos with binary features",

abstract = "Millions of surveillance cameras are currently installed in public places around the world, making it necessary to intelligently analyse the acquired data to detect the occurrence of abnormal events. A vast number of methods to detect such events have been recently proposed; unfortunately, there is a lack of methods capable of detecting these events as frames are acquired, also known as online processing. In this paper, we present an online framework for video anomaly detection that employs binary features to encode motion information, and low-complexity probabilistic models for detection. Evaluation results on the popular UCSD dataset and on a recently introduced real-event video surveillance dataset show that our framework outperforms non-online and online methods.",

keywords = "Binary features, Anomaly detection, Video anomaly detection, Computational modeling, Cameras, Surveillance, Dictionaries",

author = "Roberto Leyva and Victor Sanchez and Li, {Chang Tsun}",

note = "Includes bibliographical references.; 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing : ICASSP 2018, Signal processing and artificial intelligence: Changing the world ; Conference date: 15-04-2018 Through 20-04-2018",

year = "2018",

month = sep,

day = "13",

doi = "10.1109/ICASSP.2018.8461759",

language = "English",

isbn = "9781538646588",

pages = "1318--1322",

booktitle = "2018 IEEE International conference on acoustics, speech, and signal processing (ICASSP)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

edition = "April 2018",

url = "https://2018.ieeeicassp.org/",

}

Leyva, R, Sanchez, V & Li, CT 2018, Fast detection of abnormal events in videos with binary features. in 2018 IEEE International conference on acoustics, speech, and signal processing (ICASSP). April 2018 edn, 8461759, IEEE, Institute of Electrical and Electronics Engineers, pp. 1318-1322, 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, Calgary, Alberta, Canada, 15/04/18. https://doi.org/10.1109/ICASSP.2018.8461759

Fast detection of abnormal events in videos with binary features. / Leyva, Roberto; Sanchez, Victor; Li, Chang Tsun.
2018 IEEE International conference on acoustics, speech, and signal processing (ICASSP). April 2018. ed. IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1318-1322 8461759.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Fast detection of abnormal events in videos with binary features

AU - Leyva, Roberto

AU - Sanchez, Victor

AU - Li, Chang Tsun

N1 - Includes bibliographical references.

PY - 2018/9/13

Y1 - 2018/9/13

N2 - Millions of surveillance cameras are currently installed in public places around the world, making it necessary to intelligently analyse the acquired data to detect the occurrence of abnormal events. A vast number of methods to detect such events have been recently proposed; unfortunately, there is a lack of methods capable of detecting these events as frames are acquired, also known as online processing. In this paper, we present an online framework for video anomaly detection that employs binary features to encode motion information, and low-complexity probabilistic models for detection. Evaluation results on the popular UCSD dataset and on a recently introduced real-event video surveillance dataset show that our framework outperforms non-online and online methods.

AB - Millions of surveillance cameras are currently installed in public places around the world, making it necessary to intelligently analyse the acquired data to detect the occurrence of abnormal events. A vast number of methods to detect such events have been recently proposed; unfortunately, there is a lack of methods capable of detecting these events as frames are acquired, also known as online processing. In this paper, we present an online framework for video anomaly detection that employs binary features to encode motion information, and low-complexity probabilistic models for detection. Evaluation results on the popular UCSD dataset and on a recently introduced real-event video surveillance dataset show that our framework outperforms non-online and online methods.

KW - Binary features

KW - Anomaly detection

KW - Video anomaly detection

KW - Computational modeling

KW - Cameras

KW - Surveillance

KW - Dictionaries

UR - http://www.scopus.com/inward/record.url?scp=85054241153&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054241153&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2018.8461759

DO - 10.1109/ICASSP.2018.8461759

M3 - Conference paper

AN - SCOPUS:85054241153

SN - 9781538646588

SP - 1318

EP - 1322

BT - 2018 IEEE International conference on acoustics, speech, and signal processing (ICASSP)

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 15 April 2018 through 20 April 2018

ER -

Fast detection of abnormal events in videos with binary features

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this