University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Small-scale Anomaly Detection in Panoramic Imaging using Neural Models of Low-level Vision

Casey, MC, Hickman, DL, Pavlou, A and Sadler, JRE (2011) Small-scale Anomaly Detection in Panoramic Imaging using Neural Models of Low-level Vision In: SDisplay Technologies and Applications for Defense, Security, and Avionics V; and Enhanced and Synthetic Vision 2011, 2011-04-25 - 2011-04-29, Florida.

[img]
Preview
PDF
2011_casey_hickman_pavlou_sadler_anomaly_detection.pdf
Available under License : See the attached licence file.

Download (1032Kb)
[img] Plain Text (licence)
licence.txt

Download (1516b)

Abstract

Our understanding of sensory processing in animals has reached the stage where we can exploit neurobiological principles in commercial systems. In human vision, one brain structure that offers insight into how we might detect anomalies in real-time imaging is the superior colliculus (SC). The SC is a small structure that rapidly orients our eyes to a movement, sound or touch that it detects, even when the stimulus may be on a small-scale; think of a camouflaged movement or the rustle of leaves. This automatic orientation allows us to prioritize the use of our eyes to raise awareness of a potential threat, such as a predator approaching stealthily. In this paper we describe the application of a neural network model of the SC to the detection of anomalies in panoramic imaging. The neural approach consists of a mosaic of topographic maps that are each trained using competitive Hebbian learning to rapidly detect image features of a pre-defined shape and scale. What makes this approach interesting is the ability of the competition between neurons to automatically filter noise, yet with the capability of generalizing the desired shape and scale. We will present the results of this technique applied to the real-time detection of obscured targets in visible-band panoramic CCTV images. Using background subtraction to highlight potential movement, the technique is able to correctly identify targets which span as little as 3 pixels wide while filtering small-scale noise.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: panoramic imaging, neural networks, anomaly detection, low-level vision
Related URLs:
Divisions: Faculty of Engineering and Physical Sciences > Computing Science
Depositing User: Symplectic Elements
Date Deposited: 17 Jun 2011 14:24
Last Modified: 08 Nov 2013 12:07
URI: http://epubs.surrey.ac.uk/id/eprint/3038

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800