dc.identifier.uri |
http://dx.doi.org/10.15488/12620 |
|
dc.identifier.uri |
https://www.repo.uni-hannover.de/handle/123456789/12720 |
|
dc.contributor.author |
Cabezas, Mariano
|
|
dc.contributor.author |
Kentsch, Sarah
|
|
dc.contributor.author |
Tomhave, Luca
|
|
dc.contributor.author |
Gross, Jens
|
|
dc.contributor.author |
Caceres, Maximo Larry Lopez
|
|
dc.contributor.author |
Diez, Yago
|
|
dc.date.accessioned |
2022-08-04T08:31:55Z |
|
dc.date.available |
2022-08-04T08:31:55Z |
|
dc.date.issued |
2020 |
|
dc.identifier.citation |
Cabezas, M.; Kentsch, S.; Tomhave, L.; Gross, J.; Caceres, M.L.L. et al.: Detection of invasive species in Wetlands: Practical dl with heavily imbalanced data. In: Remote Sensing 12 (2020), Nr. 20, 3431. DOI: https://doi.org/10.3390/rs12203431 |
|
dc.description.abstract |
Deep Learning (DL) has become popular due to its ease of use and accuracy, with Transfer Learning (TL) effectively reducing the number of images needed to solve environmental problems. However, this approach has some limitations which we set out to explore: Our goal is to detect the presence of an invasive blueberry species in aerial images of wetlands. This is a key problem in ecosystem protection which is also challenging in terms of DL due to the severe imbalance present in the data. Results for the ResNet50 network show a high classification accuracy while largely ignoring the blueberry class, rendering these results of limited practical interest to detect that specific class. Moreover, by using loss function weighting and data augmentation results more akin to our practical application, our goals can be obtained. Our experiments regarding TL show that ImageNet weights do not produce satisfactory results when only the final layer of the network is trained. Furthermore, only minor gains are obtained compared with random weights when the whole network is retrained. Finally, in a study of state-of-the-art DL architectures best results were obtained by the ResNeXt architecture with 93.75 True Positive Rate and 98.11 accuracy for the Blueberry class with ResNet50, Densenet, and wideResNet obtaining close results. © 2020 by the authors. Licensee MDPI, Basel, Switzerland. |
eng |
dc.language.iso |
eng |
|
dc.publisher |
Basel : MDPI AG |
|
dc.relation.ispartofseries |
Remote Sensing 12 (2020), Nr. 20 |
|
dc.rights |
CC BY 4.0 Unported |
|
dc.rights.uri |
https://creativecommons.org/licenses/by/4.0/ |
|
dc.subject |
Antennas |
eng |
dc.subject |
Deep learning |
eng |
dc.subject |
Network layers |
eng |
dc.subject |
Transfer learning |
eng |
dc.subject |
Wetlands |
eng |
dc.subject |
Classification accuracy |
eng |
dc.subject |
Data augmentation |
eng |
dc.subject |
Ecosystem protection |
eng |
dc.subject |
Environmental problems |
eng |
dc.subject |
Imbalanced data |
eng |
dc.subject |
Invasive species |
eng |
dc.subject |
State of the art |
eng |
dc.subject |
True positive rates |
eng |
dc.subject |
Network architecture |
eng |
dc.subject |
Data analysis |
eng |
dc.subject |
Deep learning |
eng |
dc.subject |
Transfer learning |
eng |
dc.subject |
Unbalanced data |
eng |
dc.subject |
Unmanned aerial vehicles (UAV)-acquired images |
eng |
dc.subject.ddc |
620 | Ingenieurwissenschaften und Maschinenbau
|
ger |
dc.title |
Detection of invasive species in Wetlands: Practical dl with heavily imbalanced data |
|
dc.type |
Article |
|
dc.type |
Text |
|
dc.relation.essn |
2072-4292 |
|
dc.relation.doi |
https://doi.org/10.3390/rs12203431 |
|
dc.bibliographicCitation.issue |
20 |
|
dc.bibliographicCitation.volume |
12 |
|
dc.bibliographicCitation.firstPage |
3431 |
|
dc.description.version |
publishedVersion |
|
tib.accessRights |
frei zug�nglich |
|