Detection of anomalies in surveillance scenarios using mixture models

Tomé Alonso, Adrián and Salgado Álvarez de Sotomayor, Luis (2017). Detection of anomalies in surveillance scenarios using mixture models. In: "International Carnahan Conference on Security Technology (ICCST), 2017", 23/10/2017 - 26/10/2017, Madrid, España. ISBN 978-1-5386-1585-0. pp. 1-4. https://doi.org/10.1109/CCST.2017.8167830.

Description

Title: Detection of anomalies in surveillance scenarios using mixture models
Author/s:
  • Tomé Alonso, Adrián
  • Salgado Álvarez de Sotomayor, Luis
Item Type: Presentation at Congress or Conference (Article)
Event Title: International Carnahan Conference on Security Technology (ICCST), 2017
Event Dates: 23/10/2017 - 26/10/2017
Event Location: Madrid, España
Title of Book: Proceedings of International Carnahan Conference on Security Technology (ICCST), 2017
Título de Revista/Publicación: 2017 INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY (ICCST)
Date: December 2017
ISBN: 978-1-5386-1585-0
Subjects:
Freetext Keywords: Anomaly detection, Gaussian mixture model, robust optical flow, video-surveillance
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

In this paper we present a robust and simple method for the detection of anomalies in surveillance scenarios. We use a “bottom-up” approach that avoids any object tracking, making the system suitable for anomaly detection in crowds. A robust optical flow method is used for the extraction of accurate spatio-temporal motion information, which allows to get simple but discriminative descriptors that are employed to train a Gaussian mixture model. We evaluate our system in a publicly available dataset, concluding that our method outperforms similar anomaly detection approaches but with a simpler model and low-sized descriptors.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of Spainproject RTC-2015-3527-1BEGISEUnspecifiedUnspecified

More information

Item ID: 50878
DC Identifier: http://oa.upm.es/50878/
OAI Identifier: oai:oa.upm.es:50878
DOI: 10.1109/CCST.2017.8167830
Official URL: https://ieeexplore.ieee.org/document/8167830/
Deposited by: Memoria Investigacion
Deposited on: 29 May 2018 16:52
Last Modified: 29 May 2018 16:52
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM