Domain anomaly detection in machine perception: a system architecture and taxonomy

Kittler, Josef and Christmas, William and De Campos, Teofilo and Windridge, David and Yan, Fei and Illingworth, J. and Osman, M. (2014) Domain anomaly detection in machine perception: a system architecture and taxonomy. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 36 (5). pp. 845-859. ISSN 0162-8828

Full text is not in this repository.

Abstract

We address the problem of anomaly detection in machine perception. The concept of domain anomaly is introduced
as distinct from the conventional notion of anomaly used in
the literature. We propose a unified framework for anomaly
detection which exposes the multifacetted nature of anomalies
and suggest effective mechanisms for identifying and distinguishing each facet as instruments for domain anomaly detection.
The framework draws on the Bayesian probabilistic reasoning
apparatus which clearly defines concepts such as outlier, noise,
distribution drift, novelty detection (object, object primitive),
rare events, and unexpected events. Based on these concepts
we provide a taxonomy of domain anomaly events. One of the
mechanisms helping to pinpoint the nature of anomaly is based
on detecting incongruence between contextual and noncontextual sensor(y) data interpretation. The proposed methodology has wide applicability. It underpins in a unified way the anomaly detection applications found in the literature.

Item Type: Article
Keywords (uncontrolled): inference mechanisms;object detection;video signal processing;Bayesian probabilistic reasoning apparatus;contextual sensor data interpretation;domain anomaly concept;domain anomaly detection;machine perception;noncontextual sensor data interpretation;video annotation system;Bayes methods;Cognition;Computational modeling;Context;Data models;Detectors;Probabilistic logic;Domain anomaly;anomaly detection framework;anomaly detection mechanisms;machine perception
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 15323
Useful Links:
Depositing User: David Windridge
Date Deposited: 27 Apr 2015 10:26
Last Modified: 13 Oct 2016 14:33
URI: http://eprints.mdx.ac.uk/id/eprint/15323

Actions (login required)

Edit Item Edit Item