Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks

Boulze, Hugo; Korosov, Anton; Brajard, Julien

doi:10.3390/rs12132165

Cited by 91 publications

(72 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Charlotte Pelletier's team researched the robustness of random forests on remote sensing images [7]. Hugo Boulze et al [8] proposed an algorithm to classify features in remote sensing images using convolutional neural networks. Daniel Laumer's team used deep learning based on Google street-view to realize the detection of border trees in order to achieve city beautification [9].…”

Section: Application Of Target Detection and Deep Learning In Remote mentioning

confidence: 99%

“…The remote sensing data set used in this research has the characteristics of wide coverage and easy access, and is based on the application of deep learning described in research [6,7,[9][10][11] in remote sensing, combined with an existing research [4,5,8] target detection algorithm. The availability of remote sensing images has related improvements to the above-mentioned traffic monitoring methods.…”

mentioning

confidence: 99%

See 1 more Smart Citation

An Improved Traffic Congestion Monitoring System Based on Federated Learning

Mao

2020

Information

View full text Add to dashboard Cite

This study introduces a software-based traffic congestion monitoring system. The transportation system controls the traffic between cities all over the world. Traffic congestion happens not only in cities, but also on highways and other places. The current transportation system is not satisfactory in the area without monitoring. In order to improve the limitations of the current traffic system in obtaining road data and expand its visual range, the system uses remote sensing data as the data source for judging congestion. Since some remote sensing data needs to be kept confidential, this is a problem to be solved to effectively protect the safety of remote sensing data during the deep learning training process. Compared with the general deep learning training method, this study provides a federated learning method to identify vehicle targets in remote sensing images to solve the problem of data privacy in the training process of remote sensing data. The experiment takes the remote sensing image data sets of Los Angeles Road and Washington Road as samples for training, and the training results can achieve an accuracy of about 85%, and the estimated processing time of each image can be as low as 0.047 s. In the final experimental results, the system can automatically identify the vehicle targets in the remote sensing images to achieve the purpose of detecting congestion.

show abstract

Section: Application Of Target Detection and Deep Learning In Remote mentioning

confidence: 99%

mentioning

confidence: 99%

An Improved Traffic Congestion Monitoring System Based on Federated Learning

Mao

2020

Information

View full text Add to dashboard Cite

show abstract

“…Traditional remote sensing detection data include SAR and optical remote sensing data with a high spatial resolution and high spectral resolution (such as MODIS, Sentinel-2, and Landsat). As an active microwave imaging radar, SAR has the characteristics of having an all-day, all-weather, and multi-perspective collection method with a strong penetration, and its images contain rich texture information [2], achieving good results in sea ice classification [3][4][5]. With the continuous development of optical remote sensing technology, the multi/hyperspectral resolution of optical remote sensing images can now provide more detailed information in the spectral dimension, which provides important data support for the classification of sea ice images.…”

Section: Introductionmentioning

confidence: 99%

Sea Ice Image Classification Based on Heterogeneous Data Fusion and Deep Learning

et al. 2021

View full text Add to dashboard Cite

Sea ice is one of the typical causes of marine disasters. Sea ice image classification is an important component of sea ice detection. Optical data contain rich spectral information, but they do not allow one to easily distinguish between ground objects with a similar spectrum and foreign objects with the same spectrum. Synthetic aperture radar (SAR) data contain rich texture information, but the data usually have a single source. The limitation of single-source data is that they do not allow for further improvements of the accuracy of remote sensing sea ice classification. In this paper, we propose a method for sea ice image classification based on deep learning and heterogeneous data fusion. Utilizing the advantages of convolutional neural networks (CNNs) in terms of depth feature extraction, we designed a deep learning network structure for SAR and optical images and achieve sea ice image classification through feature extraction and a feature-level fusion of heterogeneous data. For the SAR images, the improved spatial pyramid pooling (SPP) network was used and texture information on sea ice at different scales was extracted by depth. For the optical data, multi-level feature information on sea ice such as spatial and spectral information on different types of sea ice was extracted through a path aggregation network (PANet), which enabled low-level features to be fully utilized due to the gradual feature extraction of the convolution neural network. In order to verify the effectiveness of the method, two sets of heterogeneous sentinel satellite data were used for sea ice classification in the Hudson Bay area. The experimental results show that compared with the typical image classification methods and other heterogeneous data fusion methods, the method proposed in this paper fully integrates multi-scale and multi-level texture and spectral information from heterogeneous data and achieves a better classification effect (96.61%, 95.69%).

show abstract

“…A patch size corresponding to 18 × 18 km ground distance is used. In [23], a CNN methodology is applied to Sentinel-1 dualpolarized HH/HV data for the classification of sea ice types in four classes (ice free, young ice, first-year ice and old ice). Two CNNs are trained over two subsets of 44 and 255 SAR scenes acquired in January-March 2018 and January-February 2020, respectively.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Categorized Sea Ice Concentration From Sentinel-1 SAR Images Based on a Fully Convolutional Network

Gélis

Colin

Longépé

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The consistent and long-term spaceborne Synthetic Aperture Radar (SAR) missions such as Sentinel-1 (S-1) provide high quality dual-polarized C-band images particularly suited to sea ice monitoring. SAR data is currently the primary source of information for sea ice charting made by human ice experts as a result of its integration with multiple information sources at different scales (mainly radiometers). The rise of deep learning now opens the prospect of automatic sea ice mapping. In this study, we investigate the potential of a Fully Convolutional Network (FCN) for the automatic estimation of Sea Ice Concentration (SIC). With input data down-sampled at 200 meters and an FCN architecture (depth and receptive field) duly parameterized, our approach is to mimic the work of an analyst who considers general context and does not necessarily use the highest possible resolution but speckle-noise polluted data. A comprehensive database is generated with 1320 dual-polarized S-1 scenes collocated with ice charts produced by MET Norway. A dedicated attention is paid to seasonal representativeness to ensure adequate performance for all sea ice types. Even if the FCN output is modeled as a categorical problem, the proposed architecture accounts for the semantic distances between SIC classes by introducing an auxiliary loss. A comparative benchmark with Ocean and Sea Ice Satellite Application Facility (OSISAF) and MET Norway SIC products is carried out, showing an Overall Accuracy of 78.2% for our 6-class classification approach. The FCN model is shown to be evenly robust to sea ice seasonal variability and incidence angle.

show abstract

Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks

Cited by 91 publications

References 20 publications

An Improved Traffic Congestion Monitoring System Based on Federated Learning

An Improved Traffic Congestion Monitoring System Based on Federated Learning

Sea Ice Image Classification Based on Heterogeneous Data Fusion and Deep Learning

Prediction of Categorized Sea Ice Concentration From Sentinel-1 SAR Images Based on a Fully Convolutional Network

Contact Info

Product

Resources

About