Deep Active Contour Models for Delineating Glacier Calving Fronts
We present a deep active contour model for detecting and delineating glacier calving fronts from satellite imagery. Contrary to existing deep learning-based calving front detectors, our model does not perform an intermediate segmentation or pixel-wise edge detection, but instead directly predicts th...
Published in: | IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium |
---|---|
Main Authors: | , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
IEEE - Institute of Electrical and Electronics Engineers
2022
|
Subjects: | |
Online Access: | https://elib.dlr.de/193327/ https://elib.dlr.de/193327/1/Deep_Active_Contour_Models_for_Delineating_Glacier_Calving_Fronts.pdf https://ieeexplore.ieee.org/document/9884819 |
id |
ftdlr:oai:elib.dlr.de:193327 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:193327 2024-05-19T07:40:42+00:00 Deep Active Contour Models for Delineating Glacier Calving Fronts Heidler, Konrad Mou, LiChao Löbel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang 2022 application/pdf https://elib.dlr.de/193327/ https://elib.dlr.de/193327/1/Deep_Active_Contour_Models_for_Delineating_Glacier_Calving_Fronts.pdf https://ieeexplore.ieee.org/document/9884819 en eng IEEE - Institute of Electrical and Electronics Engineers https://elib.dlr.de/193327/1/Deep_Active_Contour_Models_for_Delineating_Glacier_Calving_Fronts.pdf Heidler, Konrad und Mou, LiChao und Löbel, Erik und Scheinert, Mirko und Lefèvre, Sébastien und Zhu, Xiao Xiang (2022) Deep Active Contour Models for Delineating Glacier Calving Fronts. In: International Geoscience and Remote Sensing Symposium (IGARSS), Seiten 4490-4493. IEEE - Institute of Electrical and Electronics Engineers. IGARSS 2022, 2022-07-17 - 2022-07-22, Kuala Lumpur, Malaysia. doi:10.1109/IGARSS46834.2022.9884819 <https://doi.org/10.1109/IGARSS46834.2022.9884819>. EO Data Science Konferenzbeitrag PeerReviewed 2022 ftdlr https://doi.org/10.1109/IGARSS46834.2022.9884819 2024-04-25T01:05:25Z We present a deep active contour model for detecting and delineating glacier calving fronts from satellite imagery. Contrary to existing deep learning-based calving front detectors, our model does not perform an intermediate segmentation or pixel-wise edge detection, but instead directly predicts the contour parametrized by a fixed number of vertices. The model works by first deriving feature maps from an input image, and then updating an initial contour in an iterative fashion. Evaluating on the CALFIN dataset, which maps calving fronts in Greenland, our model outperforms existing approaches. Code for the experiments and animated predictions can be found at https://github.com/khdlr/deep-acm Conference Object glacier Greenland German Aerospace Center: elib - DLR electronic library IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium 4490 4493 |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
English |
topic |
EO Data Science |
spellingShingle |
EO Data Science Heidler, Konrad Mou, LiChao Löbel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang Deep Active Contour Models for Delineating Glacier Calving Fronts |
topic_facet |
EO Data Science |
description |
We present a deep active contour model for detecting and delineating glacier calving fronts from satellite imagery. Contrary to existing deep learning-based calving front detectors, our model does not perform an intermediate segmentation or pixel-wise edge detection, but instead directly predicts the contour parametrized by a fixed number of vertices. The model works by first deriving feature maps from an input image, and then updating an initial contour in an iterative fashion. Evaluating on the CALFIN dataset, which maps calving fronts in Greenland, our model outperforms existing approaches. Code for the experiments and animated predictions can be found at https://github.com/khdlr/deep-acm |
format |
Conference Object |
author |
Heidler, Konrad Mou, LiChao Löbel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang |
author_facet |
Heidler, Konrad Mou, LiChao Löbel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang |
author_sort |
Heidler, Konrad |
title |
Deep Active Contour Models for Delineating Glacier Calving Fronts |
title_short |
Deep Active Contour Models for Delineating Glacier Calving Fronts |
title_full |
Deep Active Contour Models for Delineating Glacier Calving Fronts |
title_fullStr |
Deep Active Contour Models for Delineating Glacier Calving Fronts |
title_full_unstemmed |
Deep Active Contour Models for Delineating Glacier Calving Fronts |
title_sort |
deep active contour models for delineating glacier calving fronts |
publisher |
IEEE - Institute of Electrical and Electronics Engineers |
publishDate |
2022 |
url |
https://elib.dlr.de/193327/ https://elib.dlr.de/193327/1/Deep_Active_Contour_Models_for_Delineating_Glacier_Calving_Fronts.pdf https://ieeexplore.ieee.org/document/9884819 |
genre |
glacier Greenland |
genre_facet |
glacier Greenland |
op_relation |
https://elib.dlr.de/193327/1/Deep_Active_Contour_Models_for_Delineating_Glacier_Calving_Fronts.pdf Heidler, Konrad und Mou, LiChao und Löbel, Erik und Scheinert, Mirko und Lefèvre, Sébastien und Zhu, Xiao Xiang (2022) Deep Active Contour Models for Delineating Glacier Calving Fronts. In: International Geoscience and Remote Sensing Symposium (IGARSS), Seiten 4490-4493. IEEE - Institute of Electrical and Electronics Engineers. IGARSS 2022, 2022-07-17 - 2022-07-22, Kuala Lumpur, Malaysia. doi:10.1109/IGARSS46834.2022.9884819 <https://doi.org/10.1109/IGARSS46834.2022.9884819>. |
op_doi |
https://doi.org/10.1109/IGARSS46834.2022.9884819 |
container_title |
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium |
container_start_page |
4490 |
op_container_end_page |
4493 |
_version_ |
1799480279515004928 |