Search
 
loader loading subjects...
cover
Anomaly Detection with a Spatio-Temporal Tracking of the Laser Spot
David Atienza, Concha Bielza, Javier Diaz, Pedro Larrañaga
137 - 142
10.3233/978-1-61499-682-8-137
Frontiers in Artificial Intelligence and Applications
Volume 284: STAIRS 2016
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.

Download
Creative Commons License