Logo des Repositoriums
 

Comparing Mask R-CNN and Mask2Former architectures for individual tree crown delineation

Kurzanzeige
dc.contributor.authorRuschhaupt, Sonja
dc.contributor.authorTroles, Jonas
dc.contributor.authorSchmid, Ute
dc.contributor.editorDörr, Jörg
dc.contributor.editorSteckel, Thilo
dc.date.accessioned2025-02-04T14:37:58Z
dc.date.available2025-02-04T14:37:58Z
dc.date.issued2025
dc.description.abstractWeather anomalies caused by the anthropogenic climate crisis challenge environmental workers such as foresters with an increasing number of responsibilities. In addition to providing attractive conditions for new generations of workers, deep-learning tools can ease processes for better efficiency. Tree instance segmentation has potential for many functionalities that support arborists and foresters by detecting and classifying singular trees. In the past, Mask R-CNN was primarily applied due to its outstanding performance on the 2016 COCO dataset challenge. As an alternative, we suggest Mask2Former, which outperforms Mask R-CNN on the COCO dataset. Additionally, we test whether additional digital canopy height model data can improve training. While the latter is shown to have no, if not a negative impact on the results, Mask2Former indeed outperforms Mask R-CNN in tree instance segmentation by up to 3.8%. Our code is publicly available.2en
dc.identifier.doi10.18420/giljt2025_13
dc.identifier.eissn2944-7682
dc.identifier.isbn978-3-88579-802-6
dc.identifier.pissn2944-7682
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/45670
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartof45. GIL-Jahrestagung, Digitale Infrastrukturen für eine nachhaltige Land-, Forst- und Ernährungswirtschaft
dc.relation.ispartofseriesLecture Notes in Informatics(LNI) - Proceedings, Volume P - 358
dc.subjectindividual tree crown delineation
dc.subjectinstance segmentation
dc.subjectMask2Former
dc.titleComparing Mask R-CNN and Mask2Former architectures for individual tree crown delineationen
dc.typeText/Conference Paper
gi.citation.endPage178
gi.citation.publisherPlaceBonn
gi.citation.startPage167
gi.conference.date25/26. Februar 2025
gi.conference.locationWieselburg, Austria
gi.conference.reviewfull

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
GIL_2025_Ruschhaupt_167-178.pdf
Größe:
916.29 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P358 - 45. GIL-Jahrestagung 2025 - Fokus: Digitale Infrastrukturen für eine nachhaltige Land-, Forst- und Ernährungswirtschaft