Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

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

Publication

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

Ruschhaupt, Sonja; Troles, Jonas; Schmid, Ute (2025): Comparing Mask R-CNN and Mask2Former architectures for individual tree crown delineation, in: 45. GIL-Jahrestagung, Digitale Infrastrukturen für eine nachhaltige Land-, Forst-und Ernährungswirtschaft, Bonn: Gesellschaft für Informatik e.V., S. 167–178, doi: 10.18420/giljt2025_13.

Details

Faculty/Chair
Faculty/Professorship
Author
Ruschhaupt, Sonja
Troles, Jonas
Title of the compilation
45. GIL-Jahrestagung, Digitale Infrastrukturen für eine nachhaltige Land-, Forst-und Ernährungswirtschaft
Corporate Body
Gesellschaft für Informatik eV.
Conference
45. GIL-Jahrestagung, Wieselburg, Österreich
Publisher Information
Gesellschaft für Informatik e.V. : Bonn
Year of publication
2025
Language
English
DOI
Abstract

Weather 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.2

Keywords
individual tree crown delineation
instance segmentation
Mask2Former
Peer Reviewed
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2025-04-01

Permalink: https://fis.uni-bamberg.de/handle/uniba/107281 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.