Novelty detection in video surveillance using hierarchical neural networks

Owens, Jonathan and Hunter, Andrew and Fletcher, Eric (2002) Novelty detection in video surveillance using hierarchical neural networks. In: ICANN, 27-30 August 2002, Madrid, Spain.

Documents
Novelty detection in video surveillance using hierarchical neural networks
Novelty detection in video surveillance using hierarchical neural networks
[img]
[Download]
[img]
Preview
PDF
ICANN2002.pdf

269kB

Official URL: http://www.ii.uam.es/icann2002/

Abstract

Abstract. A hierarchical self-organising neural network is described for the detection of unusual pedestrian behaviour in video-based surveillance systems. The system is trained on a normal data set, with no prior information about the
scene under surveillance, thereby requiring minimal user input. Nodes use a trace activation rule and feedforward connections, modified so that higher layer nodes are sensitive to trajectory segments traced across the previous layer. Top layer nodes have binary lateral connections and corresponding “novelty accumulator” nodes. Lateral connections are set between co-occurring nodes, generating a signal to prevent accumulation of the novelty measure along normal sequences. In abnormal sequences the novelty accumulator nodes are allowed to increase their activity, generating an alarm state.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Abstract. A hierarchical self-organising neural network is described for the detection of unusual pedestrian behaviour in video-based surveillance systems. The system is trained on a normal data set, with no prior information about the scene under surveillance, thereby requiring minimal user input. Nodes use a trace activation rule and feedforward connections, modified so that higher layer nodes are sensitive to trajectory segments traced across the previous layer. Top layer nodes have binary lateral connections and corresponding “novelty accumulator” nodes. Lateral connections are set between co-occurring nodes, generating a signal to prevent accumulation of the novelty measure along normal sequences. In abnormal sequences the novelty accumulator nodes are allowed to increase their activity, generating an alarm state.
Keywords:Video Surveillance, Neural network, Surveillance
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
ID Code:1900
Deposited By: Tammie Farley
Deposited On:21 Jul 2009 07:55
Last Modified:13 Mar 2013 08:32

Repository Staff Only: item control page