Conditional Random Fields for Improving Deep Learning-Based Glacier Calving Front Delineations
www.idp-mocca.forschung.fau.de
Measuring and Modelling Mountain Glaciers and Ice Caps in a Changing ClimAte
www.idp-mocca.forschung.fau.de
Measuring and Modelling Mountain Glaciers and Ice Caps in a Changing ClimAte
Advancements in Deep Learning have enabled the automated identification of glacier calving fronts in satellite imagery. This study improves the accuracy of this process by incorporating a Conditional Random Field (CRF) into the post-processing of the neural network’s predictions. Experiments using the CaFFe dataset showed a 27-meter improvement in mean distance error. The code is available at https://github.com/EntChanelt/GlacierCRF.
https://ieeexplore.ieee.org/document/10282915