MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES

MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES

Anomaly detection from hyperspectral data needs computationally efficient methods to process the data when the data gathering platform is a drone or a cube satellite. In this study, we introduce a minimal learning machine for hyperspectral anomaly detection. Minimal learning machine is a novel dista...

Full description

Bibliographic Details
Main Authors: I. Pölönen, K. Riihiaho, A.-M. Hakola, L. Annala
Format: Article
Language:English
Published: Copernicus Publications 2020-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2020/467/2020/isprs-archives-XLIII-B3-2020-467-2020.pdf
id doaj-3d3b25f540d64d27a93c20a5c79e172c
record_format Article
spelling doaj-3d3b25f540d64d27a93c20a5c79e172c2020-11-25T03:45:19ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342020-08-01XLIII-B3-202046747210.5194/isprs-archives-XLIII-B3-2020-467-2020MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGESI. Pölönen0K. Riihiaho1A.-M. Hakola2L. Annala3Faculty of Information Technology, University of Jyväskylä, 40100, Jyväskylä, FinlandFaculty of Information Technology, University of Jyväskylä, 40100, Jyväskylä, FinlandFaculty of Information Technology, University of Jyväskylä, 40100, Jyväskylä, FinlandFaculty of Information Technology, University of Jyväskylä, 40100, Jyväskylä, FinlandAnomaly detection from hyperspectral data needs computationally efficient methods to process the data when the data gathering platform is a drone or a cube satellite. In this study, we introduce a minimal learning machine for hyperspectral anomaly detection. Minimal learning machine is a novel distance-based classification algorithm, which is now modified to detect anomalies. Besides being computationally efficient, minimal learning machine is also easy to implement. Based on the results, we show that minimal learning machine is efficient in detecting global anomalies from the hyperspectral data with low false alarm rate.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2020/467/2020/isprs-archives-XLIII-B3-2020-467-2020.pdf
collection DOAJ
language English
format Article
sources DOAJ
author I. Pölönen
K. Riihiaho
A.-M. Hakola
L. Annala
spellingShingle I. Pölönen
K. Riihiaho
A.-M. Hakola
L. Annala
MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
author_facet I. Pölönen
K. Riihiaho
A.-M. Hakola
L. Annala
author_sort I. Pölönen
title MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES
title_short MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES
title_full MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES
title_fullStr MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES
title_full_unstemmed MINIMAL LEARNING MACHINE IN ANOMALY DETECTION FROM HYPERSPECTRAL IMAGES
title_sort minimal learning machine in anomaly detection from hyperspectral images
publisher Copernicus Publications
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
issn 1682-1750
2194-9034
publishDate 2020-08-01
description Anomaly detection from hyperspectral data needs computationally efficient methods to process the data when the data gathering platform is a drone or a cube satellite. In this study, we introduce a minimal learning machine for hyperspectral anomaly detection. Minimal learning machine is a novel distance-based classification algorithm, which is now modified to detect anomalies. Besides being computationally efficient, minimal learning machine is also easy to implement. Based on the results, we show that minimal learning machine is efficient in detecting global anomalies from the hyperspectral data with low false alarm rate.
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2020/467/2020/isprs-archives-XLIII-B3-2020-467-2020.pdf
work_keys_str_mv AT ipolonen minimallearningmachineinanomalydetectionfromhyperspectralimages
AT kriihiaho minimallearningmachineinanomalydetectionfromhyperspectralimages
AT amhakola minimallearningmachineinanomalydetectionfromhyperspectralimages
AT lannala minimallearningmachineinanomalydetectionfromhyperspectralimages
_version_ 1724510178370387968

Similar Items