• search hit 1 of 9
Back to Result List

Field Geometry and the Spatial and Temporal Generalization of Crop Classification Algorithms - A randomized Approach to compare Pixel based and Convolution based Methods

  • With the ongoing trend towards deep learning in the remote sensing community, classical pixel based algorithms are often outperformed by convolution based image segmentation algorithms. This performance was mostly validated spatially, by splitting training and validation pixels for a given year. Though generalizing models temporally is potentially more difficult, it has been a recent trend to transfer models from one year to another, and therefore to validate temporally. The study argues that it is always important to check both, in order to generate models that are useful beyond the scope of the training data. It shows that convolutional neural networks have potential to generalize better than pixel based models, since they do not rely on phenological development alone, but can also consider object geometry and texture. The UNET classifier was able to achieve the highest F1 scores, averaging 0.61 in temporal validation samples, and 0.77 in spatial validation samples. The theoretical potential for overfitting geometry and just memorizing the shape of fields that are maize has been shown to be insignificant in practical applications. In conclusion, kernel based convolutions can offer a large contribution in making agricultural classification models more transferable, both to other regions and to other years.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Mario Gilcher, Thomas Udelhoven
URN:urn:nbn:de:hbz:385-1-16748
DOI:https://doi.org/10.3390/rs13040775
Parent Title (English):Remote Sensing
Publisher:MDPI
Place of publication:Basel
Document Type:Article
Language:English
Date of completion:2021/02/20
Date of publication:2021/02/20
Publishing institution:Universität Trier
Contributing corporation:The publication was funded by the Open Access Fund of Universität Trier and the German Research Foundation (DFG)
Release Date:2021/09/08
Tag:deep learning; image segmentation; sentinel 1
GND Keyword:Deep learning; Fernerkundung; Klassifikation; Nutzpflanzen
Issue / no.:13/4
Number of pages:20
Institutes:Fachbereich 6 / Geographie und Geowissenschaften
Dewey Decimal Classification:9 Geschichte und Geografie / 90 Geschichte / 900 Geschichte und Geografie
Licence (German):License LogoCC BY: Creative-Commons-Lizenz 4.0 International

$Rev: 13581 $