Please use this identifier to cite or link to this item:
Title: A Hardware-Friendly Anomaly Detector for Real-Time Applications with Push-Broom Scanners
Authors: Diaz, Maria
Guerra, Raul 
Lopez, Sebastian 
Keywords: Anomaly Detection
Floating-Point Arithmetic
Hyperspectral Imaging
Integer Arithmetic
Push-Broom Sensor
Real-Time Applications
Issue Date: 2019
Journal: Workshop On Hyperspectral Image And Signal Processing, Evolution In Remote Sensing
Abstract: © 2019 IEEE. In this work, we propose a hardware-friendly anomaly detector as a modified version of the LbL-FAD, named HW-LbL-FAD, specifically designed for being executed into parallel hardware devices with limited computational resources. As the original LbL-FAD, the HW-LbL-FAD makes use of the orthogonal projection concept for identifying the subspace in which the background pixels are contained, thus identifying the anomalous pixels as those not totally contained in this subspace. However, the HW-LbL-FAD makes a more efficient use of the Modified Gram-Schmidt orthogonalization process, resulting in a mathematically equivalent algorithm that requires less computational and memory resources. Additionally, the HW-LbL-FAD algorithm can be totally executed using integer arithmetic at different levels of precision that can be adapted for achieving the best relation between detection accuracy and computational burden. The HW-LbL-FAD has been tested in this work using 3 real hyperspectral images typically employed for validating anomaly detection application. These images have been analyzed using both floating-point arithmetic and integer arithmetic with different levels of precision. The obtained results demonstrate the goodness of this proposal.
ISBN: 9781728152943
ISSN: 2158-6276
DOI: 10.1109/WHISPERS.2019.8921023
Source: Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing[ISSN 2158-6276],v. 2019-September
Appears in Collections:Actas de congresos
Fuentes externas
Show full item record

Page view(s)

checked on Mar 28, 2020

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.