kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
DEEPAQUA: Semantic segmentation of wetland water surfaces with SAR imagery using deep neural networks without manually annotated data
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS. Department of Physical Geography, Stockholm University,Svante Arrhenius väg 8, Stockholm, 106 91, Sweden.ORCID iD: 0009-0005-2726-3542
Department of Physical Geography, Stockholm University,Svante Arrhenius väg 8, Stockholm, 106 91, Sweden.
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0002-2748-8929
Department of Physical Geography, Stockholm University,Svante Arrhenius väg 8, Stockholm, 106 91, Sweden.
2024 (English)In: International Journal of Applied Earth Observation and Geoinformation, ISSN 1569-8432, E-ISSN 1872-826X, Vol. 126, article id 103624Article in journal (Refereed) Published
Abstract [en]

Deep learning and remote sensing techniques have significantly advanced water surface monitoring; however, the need for annotated data remains a challenge. This is particularly problematic in wetland detection, where water extent varies over time and space, demanding multiple annotations for the same area. In this paper, we present DEEPAQUA, a deep learning model inspired by knowledge distillation (a.k.a. teacher–student model) to generate labeled data automatically and eliminate the need for manual annotations during the training phase. We utilize the Normalized Difference Water Index (NDWI) as a teacher model to train a Convolutional Neural Network (CNN) for segmenting water from Synthetic Aperture Radar (SAR) images. To train the student model, we exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. DEEPAQUA represents a significant advancement in computer vision techniques for water detection by effectively training semantic segmentation models without any manually annotated data. Experimental results show that DEEPAQUA outperforms other unsupervised methods by improving accuracy by 3%, Intersection Over Union by 11%, and F1-score by 6%. This approach offers a practical solution for monitoring wetland water extent changes without the need of ground truth data, making it highly adaptable and scalable for wetland monitoring.

Place, publisher, year, edition, pages
Elsevier BV , 2024. Vol. 126, article id 103624
Keywords [en]
Automated data labeling, CNN, Deep learning, Remote sensing, Semantic segmentation, Vegetated water, Wetland mapping
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-341922DOI: 10.1016/j.jag.2023.103624ISI: 001142090200001Scopus ID: 2-s2.0-85180567035OAI: oai:DiVA.org:kth-341922DiVA, id: diva2:1824931
Note

QC 20240108

Available from: 2024-01-08 Created: 2024-01-08 Last updated: 2024-02-06Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Pena, Francisco J.Payberah, Amir H.

Search in DiVA

By author/editor
Pena, Francisco J.Payberah, Amir H.
By organisation
Software and Computer systems, SCS
In the same journal
International Journal of Applied Earth Observation and Geoinformation
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 33 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf