A Deep Active Contour Model for Delineating Glacier Calving Fronts

Research output: Contribution to journalResearch articleContributedpeer-review



Choosing how to encode a real-world problem as a machine learning task is an important design decision in machine learning. The task of the glacier calving front modeling has often been approached as a semantic segmentation task. Recent studies have shown that combining segmentation with edge detection can improve the accuracy of calving front detectors. Building on this observation, we completely rephrase the task as a contour tracing problem and propose a model for explicit contour detection that does not incorporate any dense predictions as intermediate steps. The proposed approach, called “Charting Outlines by Recurrent Adaptation” (COBRA), combines convolutional neural networks (CNNs) for feature extraction and active contour (AC) models for delineation. By training and evaluating several large-scale datasets of Greenland’s outlet glaciers, we show that this approach indeed outperforms the aforementioned methods based on segmentation and edge-detection. Finally, we demonstrate that explicit contour detection has benefits over pixel-wise methods when quantifying the models’ prediction uncertainties. The project page containing the code and animated model predictions can be found at https://khdlr.github.io/COBRA/ .


Original languageEnglish
Article number5615912
Pages (from-to)1-12
JournalIEEE Transactions on Geoscience and Remote Sensing
Publication statusPublished - 27 Jul 2023

External IDs

Scopus 85166327323
ORCID /0000-0002-0892-8941/work/142248922
ORCID /0000-0001-9874-9295/work/142255133


DFG Classification of Subject Areas according to Review Boards

Subject groups, research areas, subject areas according to Destatis


  • Active contours (ACs), edge detection, glacier front, Greenland, uncertainty