Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images
In the present study, the detection and mapping of Silybum marianum (L.) Gaertn. weed using novelty detection classifiers is reported. A multispectral camera (green-red-NIR) on board a fixed wing unmanned aerial vehicle (UAV) was employed for obtaining high-resolution images. Four novelty detection...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/17/9/2007 |
_version_ | 1811304272961208320 |
---|---|
author | Thomas K. Alexandridis Afroditi Alexandra Tamouridou Xanthoula Eirini Pantazi Anastasia L. Lagopodi Javid Kashefi Georgios Ovakoglou Vassilios Polychronos Dimitrios Moshou |
author_facet | Thomas K. Alexandridis Afroditi Alexandra Tamouridou Xanthoula Eirini Pantazi Anastasia L. Lagopodi Javid Kashefi Georgios Ovakoglou Vassilios Polychronos Dimitrios Moshou |
author_sort | Thomas K. Alexandridis |
collection | DOAJ |
description | In the present study, the detection and mapping of Silybum marianum (L.) Gaertn. weed using novelty detection classifiers is reported. A multispectral camera (green-red-NIR) on board a fixed wing unmanned aerial vehicle (UAV) was employed for obtaining high-resolution images. Four novelty detection classifiers were used to identify S. marianum between other vegetation in a field. The classifiers were One Class Support Vector Machine (OC-SVM), One Class Self-Organizing Maps (OC-SOM), Autoencoders and One Class Principal Component Analysis (OC-PCA). As input features to the novelty detection classifiers, the three spectral bands and texture were used. The S. marianum identification accuracy using OC-SVM reached an overall accuracy of 96%. The results show the feasibility of effective S. marianum mapping by means of novelty detection classifiers acting on multispectral UAV imagery. |
first_indexed | 2024-04-13T08:04:20Z |
format | Article |
id | doaj.art-0b98f2bb1d414330a1e2632cfa07988d |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-13T08:04:20Z |
publishDate | 2017-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-0b98f2bb1d414330a1e2632cfa07988d2022-12-22T02:55:13ZengMDPI AGSensors1424-82202017-09-01179200710.3390/s17092007s17092007Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral ImagesThomas K. Alexandridis0Afroditi Alexandra Tamouridou1Xanthoula Eirini Pantazi2Anastasia L. Lagopodi3Javid Kashefi4Georgios Ovakoglou5Vassilios Polychronos6Dimitrios Moshou7Laboratory of Remote Sensing and GIS, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, GreeceLaboratory of Remote Sensing and GIS, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, GreeceAgricultural Engineering Laboratory, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, GreecePlant Pathology Laboratory, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, GreeceUSDA-ARS-European Biological Control Laboratory, Tsimiski 43, 7th floor, Thessaloniki 54623, GreeceLaboratory of Remote Sensing and GIS, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, GreeceGeosense S.A., Filikis Etairias 15-17, Pylaia, Thessaloniki 55535, GreeceAgricultural Engineering Laboratory, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, GreeceIn the present study, the detection and mapping of Silybum marianum (L.) Gaertn. weed using novelty detection classifiers is reported. A multispectral camera (green-red-NIR) on board a fixed wing unmanned aerial vehicle (UAV) was employed for obtaining high-resolution images. Four novelty detection classifiers were used to identify S. marianum between other vegetation in a field. The classifiers were One Class Support Vector Machine (OC-SVM), One Class Self-Organizing Maps (OC-SOM), Autoencoders and One Class Principal Component Analysis (OC-PCA). As input features to the novelty detection classifiers, the three spectral bands and texture were used. The S. marianum identification accuracy using OC-SVM reached an overall accuracy of 96%. The results show the feasibility of effective S. marianum mapping by means of novelty detection classifiers acting on multispectral UAV imagery.https://www.mdpi.com/1424-8220/17/9/2007weedsUASRPASone-classmachine learningremote sensinggeoinformatics |
spellingShingle | Thomas K. Alexandridis Afroditi Alexandra Tamouridou Xanthoula Eirini Pantazi Anastasia L. Lagopodi Javid Kashefi Georgios Ovakoglou Vassilios Polychronos Dimitrios Moshou Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images Sensors weeds UAS RPAS one-class machine learning remote sensing geoinformatics |
title | Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images |
title_full | Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images |
title_fullStr | Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images |
title_full_unstemmed | Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images |
title_short | Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images |
title_sort | novelty detection classifiers in weed mapping silybum marianum detection on uav multispectral images |
topic | weeds UAS RPAS one-class machine learning remote sensing geoinformatics |
url | https://www.mdpi.com/1424-8220/17/9/2007 |
work_keys_str_mv | AT thomaskalexandridis noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages AT afroditialexandratamouridou noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages AT xanthoulaeirinipantazi noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages AT anastasiallagopodi noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages AT javidkashefi noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages AT georgiosovakoglou noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages AT vassiliospolychronos noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages AT dimitriosmoshou noveltydetectionclassifiersinweedmappingsilybummarianumdetectiononuavmultispectralimages |