Thomas Kræmer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Thomas Kræmer has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Andrea Marinoni
Department of Computer Science and Technology, University of Cambridge, Cambridge, U.K.
2 shared publications - Salman Khaleghian
Faculty of Science and Technology, UiT The Arctic University of Norway, Troms, Norway
2 shared publications - Torbjorn Eltoft
Department of Physics and Technology, UiT The Arctic University of Norway, Troms, Norway
2 shared publications - Agnar Sivertsen
NORCE Norwegian Research Center AS, Sykehusvn 21, 9019 Tromsø, Norway
1 shared publication Camilla Brekke
Department of Physics and Technology, UiT The Arctic University of Norway, Tromsø, Norway
1 shared publicationChristiane Hübner
1 shared publication
Latest Publications
- Open Access
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 10761-10772
Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification
In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from a limited number of labeled samples and a relatively large number of unlabeled samples. Therefore, our method addresses the key challenge of using a limited number of precisely labeled samples to achieve generalization capability by discovering the underlying sea ice characteristics also from unlabeled data. We perform experimental analysis considering a standard dataset consisting of properly labeled sea ice data spanning over different time slots of the year. Both qualitative and quantitative results obtained on this dataset show that our proposed TSLP-SSL method outperforms deep supervised and semisupervised reference methods.
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 10761-10772
Open AccessDeep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification
In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from a limited number of labeled samples and a relatively large number of unlabeled samples. Therefore, our method addresses the key challenge of using a limited number of precisely labeled samples to achieve generalization capability by discovering the underlying sea ice characteristics also from unlabeled data. We perform experimental analysis considering a standard dataset consisting of properly labeled sea ice data spanning over different time slots of the year. Both qualitative and quantitative results obtained on this dataset show that our proposed TSLP-SSL method outperforms deep supervised and semisupervised reference methods.
- Open Access
- 29 April 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (9) , 1734
Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks
We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities in the radar backscatter for certain conditions that include the reflection of complex information from sea ice surfaces. We use manually annotated SAR images containing various sea ice types to construct a dataset for our Deep Learning (DL) analysis. To avoid contamination between classes we use a combination of near-simultaneous SAR images from S1 and fine resolution cloud-free optical data from Sentinel-2 (S2). For the classification, we use data augmentation to adjust for the imbalance of sea ice type classes in the training data. The SAR images are divided into small patches which are processed one at a time. We demonstrate that the combination of data augmentation and training of a proposed modified Visual Geometric Group 16-layer (VGG-16) network, trained from scratch, significantly improves the classification performance, compared to the original VGG-16 model and an ad hoc CNN model. The experimental results show both qualitatively and quantitatively that our models produce accurate classification results.
- 29 April 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (9) , 1734
Open AccessSea Ice Classification of SAR Imagery Based on Convolution Neural Networks
We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities in the radar backscatter for certain conditions that include the reflection of complex information from sea ice surfaces. We use manually annotated SAR images containing various sea ice types to construct a dataset for our Deep Learning (DL) analysis. To avoid contamination between classes we use a combination of near-simultaneous SAR images from S1 and fine resolution cloud-free optical data from Sentinel-2 (S2). For the classification, we use data augmentation to adjust for the imbalance of sea ice type classes in the training data. The SAR images are divided into small patches which are processed one at a time. We demonstrate that the combination of data augmentation and training of a proposed modified Visual Geometric Group 16-layer (VGG-16) network, trained from scratch, significantly improves the classification performance, compared to the original VGG-16 model and an ad hoc CNN model. The experimental results show both qualitatively and quantitatively that our models produce accurate classification results.
- Open Access
- 4 March 2021
- Published by Copernicus GmbH
SIOS’s airborne remote sensing campaigns in Svalbard
Svalbard Integrated Arctic Earth Observing System (SIOS) is an international collaboration of 24 research institutions from 9 countries studying the environment and climate in and around Svalbard. The global pandemic of Coronavirus disease (Covid-19) has affected the Svalbard research in a number of ways due to nationwide lockdown in many countries, strict travel restrictions in Svalbard, and quarantine regulations. Many field campaigns to Svalbard were cancelled in 2020 and campaigns in 2021 are still uncertain. In response to this challenge, we conducted practical activities to support the Svalbard science community in filling gaps in scientific observations. One of our activities involved conducting airborne remote sensing campaigns in Svalbard to support scientific projects. In 2020, SIOS supported 10 scientific projects by conducting 25 hours of aircraft and unmanned aerial vehicle (UAV)-based data collection in Svalbard. This is one of the finest ways to fill the data gap in the current situation as it is practically possible to conduct field campaigns using airborne platforms in spite of travel restrictions. We are using the aerial camera and hyperspectral sensor installed onboard the Dornier DO228 aircraft operated by the local company Lufttransport to acquire aerial images and hyperspectral data from various locations in Svalbard. The hyperspectral sensor image the ground in 186 spectral bands covering the range 400-1000 nm. Hyperspectral data can be used to map and characterise earth, ice and ocean surface features, such as minerals, vegetation, glaciers and snow cover, colour and pollutants. Further, it can be used to make 3D models of the terrain as well as searching for the presence of animals (e.g. counting seals). In addition, aerial photos are particularly useful tool to follow the seasonal dynamic changes and extent in sea ice cover, tracking icebergs, ocean productivity (Chlorophyll a) and river runoff (turbidity). Data collected from the SIOS funded airborne missions will not only help to fill a few of the data gaps resulting from the lockdown but also will be used by glaciologists, biologists, hydrologists, and other Earth system scientists to understand the state of the environment of Svalbard during these times. In 2021, we are continuing this activity by conducting more airborne campaigns in Svalbard. In this presentation, we will specifically focus on the overview of projects supported by airborne remote sensing campaigns.
- 4 March 2021
- Published by Copernicus GmbH
Open AccessSIOS’s airborne remote sensing campaigns in Svalbard
Svalbard Integrated Arctic Earth Observing System (SIOS) is an international collaboration of 24 research institutions from 9 countries studying the environment and climate in and around Svalbard. The global pandemic of Coronavirus disease (Covid-19) has affected the Svalbard research in a number of ways due to nationwide lockdown in many countries, strict travel restrictions in Svalbard, and quarantine regulations. Many field campaigns to Svalbard were cancelled in 2020 and campaigns in 2021 are still uncertain. In response to this challenge, we conducted practical activities to support the Svalbard science community in filling gaps in scientific observations. One of our activities involved conducting airborne remote sensing campaigns in Svalbard to support scientific projects. In 2020, SIOS supported 10 scientific projects by conducting 25 hours of aircraft and unmanned aerial vehicle (UAV)-based data collection in Svalbard. This is one of the finest ways to fill the data gap in the current situation as it is practically possible to conduct field campaigns using airborne platforms in spite of travel restrictions. We are using the aerial camera and hyperspectral sensor installed onboard the Dornier DO228 aircraft operated by the local company Lufttransport to acquire aerial images and hyperspectral data from various locations in Svalbard. The hyperspectral sensor image the ground in 186 spectral bands covering the range 400-1000 nm. Hyperspectral data can be used to map and characterise earth, ice and ocean surface features, such as minerals, vegetation, glaciers and snow cover, colour and pollutants. Further, it can be used to make 3D models of the terrain as well as searching for the presence of animals (e.g. counting seals). In addition, aerial photos are particularly useful tool to follow the seasonal dynamic changes and extent in sea ice cover, tracking icebergs, ocean productivity (Chlorophyll a) and river runoff (turbidity). Data collected from the SIOS funded airborne missions will not only help to fill a few of the data gaps resulting from the lockdown but also will be used by glaciologists, biologists, hydrologists, and other Earth system scientists to understand the state of the environment of Svalbard during these times. In 2021, we are continuing this activity by conducting more airborne campaigns in Svalbard. In this presentation, we will specifically focus on the overview of projects supported by airborne remote sensing campaigns.
- 5 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 53 (12) , 6407-6418
Emulating Sentinel-1 Doppler Radial Ice Drift Measurements Using Envisat ASAR Data
Using data from the Envisat Advanced Synthetic Aperture Radar (ASAR) instrument, this paper demonstrates how the high-precision radial surface velocity product, which will become available with the European Space Agency's Sentinel-1 satellite, can complement the analysis of sea ice motion. High-resolution Doppler frequency measurements are used to estimate the subsecond line-of-sight motion of drifting sea ice in Fram Strait. We compare the method with buoy measurements and a recent cross-correlation algorithm for tracking ice between pairs of images. Maximum speeds measured from the time series were on the order of 20 cm/s. Using our method, we measured instantaneous speeds reaching 40–60 cm/s.
- 5 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 53 (12) , 6407-6418
Emulating Sentinel-1 Doppler Radial Ice Drift Measurements Using Envisat ASAR Data
Using data from the Envisat Advanced Synthetic Aperture Radar (ASAR) instrument, this paper demonstrates how the high-precision radial surface velocity product, which will become available with the European Space Agency's Sentinel-1 satellite, can complement the analysis of sea ice motion. High-resolution Doppler frequency measurements are used to estimate the subsecond line-of-sight motion of drifting sea ice in Fram Strait. We compare the method with buoy measurements and a recent cross-correlation algorithm for tracking ice between pairs of images. Maximum speeds measured from the time series were on the order of 20 cm/s. Using our method, we measured instantaneous speeds reaching 40–60 cm/s.