Delineating Standing Deadwood in High-Resolution RGB Drone Imagery
Research output: Contribution to conference › Conference abstract for conference › Research › peer-review
Standard
Delineating Standing Deadwood in High-Resolution RGB Drone Imagery. / Möhring, Jakobus; Mosig, Clemens; Cheng, Yan; Mahecha, Miguel; Priego, Oscar Perez; Beloiu, Mirela; Volpi, Michele; Horion, Stéphanie; Latifi, Hooman; Shafeian, Elham; Fassnacht, Fabian; Montero, David; Zielewska-Büttner, Katarzyna; Laliberté, Etienne; Cloutier, Myriam; Schmehl, Marie-Therese; Frick, Annett; Müller-Landau, Helene; Cushman, KC; Hupy, Joseph; Ma, Qin; Su, Yanjun; Khatri-Chhetri, Pratima; Kruse, Stefan; Frey, Julian; Schiefer, Felix; Junttila, Samuli; Potts, Alastair; Uhl, Andreas; Rossi, Christian; Kattenborn, Teja.
2024. Abstract from EGU General Assembly 2024, Vienna, Austria.Research output: Contribution to conference › Conference abstract for conference › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - ABST
T1 - Delineating Standing Deadwood in High-Resolution RGB Drone Imagery
AU - Möhring, Jakobus
AU - Mosig, Clemens
AU - Cheng, Yan
AU - Mahecha, Miguel
AU - Priego, Oscar Perez
AU - Beloiu, Mirela
AU - Volpi, Michele
AU - Horion, Stéphanie
AU - Latifi, Hooman
AU - Shafeian, Elham
AU - Fassnacht, Fabian
AU - Montero, David
AU - Zielewska-Büttner, Katarzyna
AU - Laliberté, Etienne
AU - Cloutier, Myriam
AU - Schmehl, Marie-Therese
AU - Frick, Annett
AU - Müller-Landau, Helene
AU - Cushman, KC
AU - Hupy, Joseph
AU - Ma, Qin
AU - Su, Yanjun
AU - Khatri-Chhetri, Pratima
AU - Kruse, Stefan
AU - Frey, Julian
AU - Schiefer, Felix
AU - Junttila, Samuli
AU - Potts, Alastair
AU - Uhl, Andreas
AU - Rossi, Christian
AU - Kattenborn, Teja
PY - 2024
Y1 - 2024
N2 - We have observed tree die-offs in a variety of regions in the world. Understanding the diverse causes of tree mortality requires exact information about which trees are dying and where. With the increased user-friendliness of drones and the availability of airborne imagery, high-resolution imagery of forests is becoming widely available. Delineating standing deadwood in such aerial imagery has become a classic segmentation task and several models with varying accuracy have been developed. However, these machine-learning based models are not generic and limited to specific image resolutions, sensor characteristics, geographic regions, and forest ecosystems. The reason for this lack of generality is that previous models have been trained using only datasets representative of specific regions and obtained from a single source. In this study, we obtain a diverse dataset spanning more than a dozen countries across continents and implement a single convolutional neural network (CNN) model that is able to cope with most forest ecosystems, varying image quality, and spatial resolutions.
AB - We have observed tree die-offs in a variety of regions in the world. Understanding the diverse causes of tree mortality requires exact information about which trees are dying and where. With the increased user-friendliness of drones and the availability of airborne imagery, high-resolution imagery of forests is becoming widely available. Delineating standing deadwood in such aerial imagery has become a classic segmentation task and several models with varying accuracy have been developed. However, these machine-learning based models are not generic and limited to specific image resolutions, sensor characteristics, geographic regions, and forest ecosystems. The reason for this lack of generality is that previous models have been trained using only datasets representative of specific regions and obtained from a single source. In this study, we obtain a diverse dataset spanning more than a dozen countries across continents and implement a single convolutional neural network (CNN) model that is able to cope with most forest ecosystems, varying image quality, and spatial resolutions.
U2 - 10.5194/egusphere-egu24-19025
DO - 10.5194/egusphere-egu24-19025
M3 - Conference abstract for conference
T2 - EGU General Assembly 2024
Y2 - 15 April 2024 through 19 April 2024
ER -
ID: 385222540