Automated Intrusion Detection for Video Surveillance Using Conditional Random Fields

D. Matern, A. P. Condurache, A. Mertins

Abstract

In this paper, we propose a method for intrusion de-tection in a video surveillance scenario. For this pur-pose, we train a conditional random field (CRF) onfeatures extracted from a video stream. CRFs estimatea state sequence, given a feature sequence. To detectintrusions, we analyze this state sequence. CRFs areusually trained in a supervised manner. Here, we espe-cially propose a new training algorithm for CRFs basedon expectation maximization, which can be used withunlabeled data. We apply the resulting trained CRFto separate normal activities from suspicious behavior.We have successfully tested our algorithm on 169 se-quences.
OriginalspracheEnglisch
Seiten298-301
Seitenumfang4
PublikationsstatusVeröffentlicht - 01.08.2013
VeranstaltungMVA2013 IAPR International Conference on Machine Vision Applications - Kyoto, Japan
Dauer: 20.05.201323.05.2013

Tagung, Konferenz, Kongress

Tagung, Konferenz, KongressMVA2013 IAPR International Conference on Machine Vision Applications
Land/GebietJapan
OrtKyoto
Zeitraum20.05.1323.05.13

Fingerprint

Untersuchen Sie die Forschungsthemen von „Automated Intrusion Detection for Video Surveillance Using Conditional Random Fields“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren