Logo des Repositoriums
 

Indicator plant species detection in grassland using EfficientDet object detector

Kurzanzeige
dc.contributor.authorBasavegowda, Deepak Hanike
dc.contributor.authorMosebach, Paul
dc.contributor.authorSchleip, Inga
dc.contributor.authorWeltzien, Cornelia
dc.contributor.editorGandorfer, Markus
dc.contributor.editorHoffmann, Christa
dc.contributor.editorEl Benni, Nadja
dc.contributor.editorCockburn, Marianne
dc.contributor.editorAnken, Thomas
dc.contributor.editorFloto, Helga
dc.date.accessioned2022-02-24T13:35:03Z
dc.date.available2022-02-24T13:35:03Z
dc.date.issued2022
dc.description.abstractExtensively used grasslands (meadows and pastures) are ecologically valuable areas in the agricultural landscape and part of the multifunctional agriculture. In Germany, the quality of these grasslands is assessed based on the occurrence of certain plant species known as indicator or character species, with indicators being defined at regional level. Therefore, the recognition of these indicators on a spatial level is a prerequisite for monitoring grassland biodiversity. The identification of indicator species for the status quo of grassland using traditional methods was found to be challenging and tedious. Deep learning-algorithms applied to high-resolution UAV imagery could be the key solution, where UAV with remote sensors can map a large area of grassland in comparison to manual or ground mapping methods and deep learning-algorithms can automate the detection process. In this research work, we use an EfficientDet based algorithm to train an object detection model capable of recognizing indicators on RGB data. The experimental results show that this approach is very promising in contrast to the difficult and time-consuming manual recognition methods. The model was trained with the momentum-SGD optimizer with a momentum value of 0.9 and a learning rate of 0.0001. The model was trained and tested on 1200 images and achieves 45.7 AP (and 85.7 AP50) on test data set. The dataset includes images of four distinct indicator plant species: Armeria maritima, Campanula patula, Cirsium oleraceum, and Daucus carotaen
dc.identifier.isbn978-3-88579-711-1
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/38431
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartof42. GIL-Jahrestagung, Künstliche Intelligenz in der Agrar- und Ernährungswirtschaft
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-317
dc.subjectdigital agriculture
dc.subjectindicators recognition
dc.subjectbiodiversity in grassland
dc.subjectHNV farming
dc.subjectdeep learn-ing
dc.subjectobject detection
dc.titleIndicator plant species detection in grassland using EfficientDet object detectoren
dc.typeText/Conference Paper
gi.citation.endPage62
gi.citation.publisherPlaceBonn
gi.citation.startPage57
gi.conference.date21.-22. Februar 2022
gi.conference.locationTänikon, Online

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
GIL2022_Basavegowda_57-62.pdf
Größe:
395.07 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P317 - 42. GIL-Jahrestagung 2022 - Fokus: Künstliche Intelligenz in der Agrar- und Ernährungswirtschaft