Anomaly detection with a spatio-temporal tracking of the laser spot

Atienza González, David, Bielza Lozoya, María Concepción ORCID: https://orcid.org/0000-0001-7109-2668, Díaz Rozo, Javier and Larrañaga Múgica, Pedro María ORCID: https://orcid.org/0000-0002-1885-4501 (2016). Anomaly detection with a spatio-temporal tracking of the laser spot. In: "Eighth European Starting AI Researcher Symposium", 26 Aug - 02 Sep 2016, La Haya, Holanda. ISBN 978-1-61499-681-1. pp. 137-142. https://doi.org/10.3233/978-1-61499-682-8-137.

Description

Title: Anomaly detection with a spatio-temporal tracking of the laser spot
Author/s:
Item Type: Presentation at Congress or Conference (Article)
Event Title: Eighth European Starting AI Researcher Symposium
Event Dates: 26 Aug - 02 Sep 2016
Event Location: La Haya, Holanda
Title of Book: Stairs 2016: Proceedings of the Eighth European Starting Ai Researcher Symposium
Date: 2016
ISBN: 978-1-61499-681-1
Volume: 284
Subjects:
Freetext Keywords: Kernel density estimation; Anomaly detection; Time-series; Laser surface heating process
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[thumbnail of INVE_MEM_2016_253333.pdf]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

Anomaly detection is an important problem with many applications in industry. This paper introduces a new methodology for detecting anomalies in a real laser heating surface process recorded with a high-speed thermal camera (1000 fps, 32×32 pixels). The system is trained with non-anomalous data only (32 videos with 21500 frames). The proposed method is built upon kernel density estimation and is capable of detecting anomalies in time-series data. The classification should be completed in-process, that is, within the cycle time of the workpiece.

More information

Item ID: 46642
DC Identifier: https://oa.upm.es/46642/
OAI Identifier: oai:oa.upm.es:46642
DOI: 10.3233/978-1-61499-682-8-137
Official URL: http://ebooks.iospress.nl/volumearticle/45049
Deposited by: Memoria Investigacion
Deposited on: 18 Oct 2017 10:08
Last Modified: 11 Jan 2023 08:43
  • 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