scholarly journals MARRYING DEEP LEARNING AND DATA FUSION FOR ACCURATE SEMANTIC LABELING OF SENTINEL-2 IMAGES

2021 ◽  
Vol V-3-2021 ◽  
pp. 101-107
Author(s):  
G. Fonteix ◽  
M. Swaine ◽  
M. Leras ◽  
Y. Tarabalka ◽  
S. Tripodi ◽  
...  
Keyword(s):  
Deep Learning ◽  
European Space Agency ◽  
External Source ◽  
Convolutional Network ◽  
Spectral Bands ◽  
Space Agency ◽  
Semantic Labeling ◽  
Multi Temporal ◽  
Correction Step ◽  
Sentinel 2

Abstract. The understanding of the Earth through global land monitoring from satellite images paves the way towards many applications including flight simulations, urban management and telecommunications. The twin satellites from the Sentinel-2 mission developed by the European Space Agency (ESA) provide 13 spectral bands with a high observation frequency worldwide. In this paper, we present a novel multi-temporal approach for land-cover classification of Sentinel-2 images whereby a time-series of images is classified using fully convolutional network U-Net models and then coupled by a developed probabilistic algorithm. The proposed pipeline further includes an automatic quality control and correction step whereby an external source can be introduced in order to validate and correct the deep learning classification. The final step consists of adjusting the combined predictions to the cloud-free mosaic built from Sentinel-2 L2A images in order for the classification to more closely match the reference mosaic image.

scholarly journals Oil Spill Index (OSI) to Sentinel-2 Satellite Data: QU in International Contribution

2021 ◽  
Author(s):  
S Rajendran ◽  
AS Fahad ◽  
FN Sadooni ◽  
HAS Al-Kuwari ◽  
P Vethamony ◽  
...  
Keyword(s):  
Oil Spill ◽  
Satellite Data ◽  
Emergency Preparedness ◽  
Oil Spills ◽  
European Space Agency ◽  
Optical Data ◽  
Spectral Absorption ◽  
Spectral Bands ◽  
Space Agency ◽  
Sentinel 2

An Oil Spill Index (OSI = (B3+B4)/B2) was developed and applied to Sentinel-2 optical satellite data of the European Space Agency (ESA) to map marine oil spills using spectral absorption characters of spectral bands of the Sentinel-2. The potential application of OSI and derived indices [i. (5+6)/7, (3+4)/2, (11+12)/8 and ii. 3/2, (3+4)/2, (6+7)/5] were demonstrated to the oil spills that occurred off Mauritius, Indian Ocean, on August 06, 2020, and Norilsk region, Russia on May 29, 2020, and the results were published in the peer-reviewed research journals. Recently (August 19, 2021), our methodology was recognized by the Sentinel-Hub (a repository of custom scripts) https://custom-scripts.sentinel-hub.com/sentinel-2/oil-spill-index/ for OSI calculation. We validated the remote sensing results with the drone images taken during the incident. Our OSI index is the first to be applied to Sentinel-2 optical data to map oil spills. We proved the potential of indices and the capability of Sentinel sensors to detect, map, monitor, and assess the oil spill, which can be used for emergency preparedness of oil spills.

scholarly journals Reconstruction of Cloud-free Sentinel-2 Image Time-series Using an Extended Spatiotemporal Image Fusion Approach

2020 ◽  
Vol 12 (16) ◽  
pp. 2595
Author(s):  
Fuqun Zhou ◽  
Detang Zhong ◽  
Rihana Peiman
Keyword(s):  
Time Series ◽  
Image Fusion ◽  
European Space Agency ◽  
Synthetic Image ◽  
Fusion Model ◽  
Spectral Bands ◽  
Space Agency ◽  
Image Pairs ◽  
Fusion Approach ◽  
Sentinel 2

Time-series for medium spatial resolution satellite imagery are a valuable resource for environmental assessment and monitoring at regional and local scales. Sentinel-2 satellites from the European Space Agency (ESA) feature a multispectral instrument (MSI) with 13 spectral bands and spatial resolutions from 10 m to 60 m, offering a revisit range from 5 days at the equator to a daily approach of the poles. Since their launch, the Sentinel-2 MSI image time-series from satellites have been used widely in various environmental studies. However, the values of Sentinel-2 image time-series have not been fully realized and their usage is impeded by cloud contamination on images, especially in cloudy regions. To increase cloud-free image availability and usage of the time-series, this study attempted to reconstruct a Sentinel-2 cloud-free image time-series using an extended spatiotemporal image fusion approach. First, a spatiotemporal image fusion model was applied to predict synthetic Sentinel-2 images when clear-sky images were not available. Second, the cloudy and cloud shadow pixels of the cloud contaminated images were identified based on analysis of the differences of the synthetic and observation image pairs. Third, the cloudy and cloud shadow pixels were replaced by the corresponding pixels of its synthetic image. Lastly, the pixels from the synthetic image were radiometrically calibrated to the observation image via a normalization process. With these processes, we can reconstruct a full length cloud-free Sentinel-2 MSI image time-series to maximize the values of observation information by keeping observed cloud-free pixels and calibrating the synthetized images by using the observed cloud-free pixels as references for better quality.

scholarly journals SENTINEL-2 GLOBAL REFERENCE IMAGE VALIDATION AND APPLICATION TO MULTITEMPORAL PERFORMANCES AND HIGH LATITUDE DIGITAL SURFACE MODEL

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 447-454 ◽  
Author(s):  
A. Gaudel ◽  
F. Languille ◽  
J. M. Delvit ◽  
J. Michel ◽  
M. Cournet ◽  
...  
Keyword(s):  
Image Quality ◽  
European Space Agency ◽  
Reference Image ◽  
Surface Model ◽  
Space Agency ◽  
Northern Latitudes ◽  
Quality Aspects ◽  
Multi Temporal ◽  
Temporal Registration ◽  
Sentinel 2

In the frame of the Copernicus program of the European Commission, Sentinel-2 is a constellation of 2 satellites with a revisit time of 5 days in order to have temporal images stacks and a global coverage over terrestrial surfaces. Satellite 2A was launched in June 2015, and satellite 2B will be launched in March 2017.<br><br> In cooperation with the European Space Agency (ESA), the French space agency (CNES) is in charge of the image quality of the project, and so ensures the CAL/VAL commissioning phase during the months following the launch. This cooperation is also extended to routine phase as CNES supports European Space Research Institute (ESRIN) and the Sentinel-2 Mission performance Centre (MPC) for validation in geometric and radiometric image quality aspects, and in Sentinel-2 GRI geolocation performance assessment whose results will be presented in this paper. The GRI is a set of S2A images at 10m resolution covering the whole world with a good and consistent geolocation. This ground reference enables accurate multi-temporal registration of refined Sentinel-2 products.<br><br> While not primarily intended for the generation of DSM, Sentinel-2 swaths overlap between orbits would also allow for the generation of a complete DSM of land and ices over 60° of northern latitudes (expected accuracy: few S2 pixels in altimetry). This DSM would benefit from the very frequent revisit times of Sentinel-2, to monitor ice or snow level in area of frequent changes, or to increase measurement accuracy in areas of little changes.

scholarly journals Discrimination of glacier facies using multi-temporal SAR data

1998 ◽  
Vol 44 (146) ◽  
pp. 42-53 ◽  
Author(s):  
K. C. Partington
Keyword(s):  
European Space Agency ◽  
Greenland Ice Sheet ◽  
Sensor Calibration ◽  
Lower Altitude ◽  
Mount Pinatubo ◽  
South Central ◽  
Space Agency ◽  
Wet Snow ◽  
Multi Temporal ◽  
Sar Data

AbstractGlacier facies from the Greenland ice sheet and the Wrangell-St Elias Mountains, Alaska, are analyzed using multi-temporal synthetic aperture radar (SAR) data from the European Space Agency ERS-1 satellite. Distinct zones and facies are visible in multi-temporal SAR data, including the dry-snow facies, the combined percolation and wet-snow facies, the ice facies, transient melt areas and moraine. In Greenland and south-central Alaska, very similar multi-temporal signatures are evident for the same facies, although these facies are found at lower altitude in West Greenland where the equilibrium line appears to be found at sea level at 71°30?N during the year analyzed (1992-93), probably because of the cooling effect of the eruption of Mount Pinatubo. In Greenland, both the percolation and dry-snow facies are excellent distributed targets for sensor calibration, with backscatter coefficients stable to within 0.2 dB. However, the percolation facies near the top of Mount Wrangell are more complex and less easily delineated than in Greenland, and at high altitude the glacier facies have a multi-temporal signature which depends sensitively on slope orientation.

scholarly journals Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

2018 ◽  
Vol 10 (11) ◽  
pp. 1827 ◽  
Author(s):  
Ahram Song ◽  
Jaewan Choi ◽  
Youkyung Han ◽  
Yongil Kim
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Spatial Information ◽  
Short Term Memory ◽  
Hyperspectral Images ◽  
Convolutional Network ◽  
Ground Truth Data ◽  
Fully Convolutional Network ◽  
Training Samples ◽  
Multi Temporal

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM.

scholarly journals A Deep Learning Approach for Burned Area Segmentation with Sentinel-2 Data

2020 ◽  
Vol 12 (15) ◽  
pp. 2422
Author(s):  
Lisa Knopp ◽  
Marc Wieland ◽  
Michaela Rättich ◽  
Sandro Martinis
Keyword(s):  
Deep Learning ◽  
Network Performance ◽  
Near Infrared ◽  
Remote Sensing Data ◽  
Economic Consequences ◽  
Validation Dataset ◽  
Burned Area ◽  
Burned Areas ◽  
Spectral Bands ◽  
Sentinel 2

Wildfires have major ecological, social and economic consequences. Information about the extent of burned areas is essential to assess these consequences and can be derived from remote sensing data. Over the last years, several methods have been developed to segment burned areas with satellite imagery. However, these methods mostly require extensive preprocessing, while deep learning techniques—which have successfully been applied to other segmentation tasks—have yet to be fully explored. In this work, we combine sensor-specific and methodological developments from the past few years and suggest an automatic processing chain, based on deep learning, for burned area segmentation using mono-temporal Sentinel-2 imagery. In particular, we created a new training and validation dataset, which is used to train a convolutional neural network based on a U-Net architecture. We performed several tests on the input data and reached optimal network performance using the spectral bands of the visual, near infrared and shortwave infrared domains. The final segmentation model achieved an overall accuracy of 0.98 and a kappa coefficient of 0.94.

scholarly journals OLCI A/B Tandem Phase Analysis, Part 1: Level 1 Homogenisation and Harmonisation

2020 ◽  
Vol 12 (11) ◽  
pp. 1804 ◽  
Author(s):  
Nicolas Lamquin ◽  
Sébastien Clerc ◽  
Ludovic Bourg ◽  
Craig Donlon
Keyword(s):  
European Space Agency ◽  
Companion Paper ◽  
The Other ◽  
Satellite Mission ◽  
Space Agency ◽  
The Future ◽  
Level 1 ◽  
Level 2 ◽  
Very High ◽  
Sentinel 2

Copernicus is a European system for monitoring the Earth in support of European policy. It includes the Sentinel-3 satellite mission which provides reliable and up-to-date measurements of the ocean, atmosphere, cryosphere, and land. To fulfil mission requirements, two Sentinel-3 satellites are required on-orbit at the same time to meet revisit and coverage requirements in support of Copernicus Services. The inter-unit consistency is critical for the mission as more S3 platforms are planned in the future. A few weeks after its launch in April 2018, the Sentinel-3B satellite was manoeuvred into a tandem configuration with its operational twin Sentinel-3A already in orbit. Both satellites were flown only thirty seconds apart on the same orbit ground track to optimise cross-comparisons. This tandem phase lasted from early June to mid October 2018 and was followed by a short drift phase during which the Sentinel-3B satellite was progressively moved to a specific orbit phasing of 140° separation from the sentinel-3A satellite. In this paper, an output of the European Space Agency (ESA) Sentinel-3 Tandem for Climate study (S3TC), we provide a full methodology for the homogenisation and harmonisation of the two Ocean and Land Colour Instruments (OLCI) based on the tandem phase. Homogenisation adjusts for unavoidable slight spatial and spectral differences between the two sensors and provide a basis for the comparison of the radiometry. Persistent radiometric biases of 1–2% across the OLCI spectrum are found with very high confidence. Harmonisation then consists of adjusting one instrument on the other based on these findings. Validation of the approach shows that such harmonisation then procures an excellent radiometric alignment. Performed on L1 calibrated radiances, the benefits of harmonisation are fully appreciated on Level 2 products as reported in a companion paper. Whereas our methodology aligns one sensor to behave radiometrically as the other, discussions consider the choice of the reference to be used within the operational framework. Further exploitation of the measurements indeed provides evidence of the need to perform flat-fielding on both payloads, prior to any harmonisation. Such flat-fielding notably removes inter-camera differences in the harmonisation coefficients. We conclude on the extreme usefulness of performing a tandem phase for the OLCI mission continuity as well as for any optical mission to which the methodology presented in this paper applies (e.g., Sentinel-2). To maintain the climate record, it is highly recommended that the future Sentinel-3C and Sentinel-3D satellites perform tandem flights when injected into the Sentinel-3 time series.

scholarly journals Crop Mapping Using Random Forest and Particle Swarm Optimization based on Multi-Temporal Sentinel-2

2020 ◽  
Vol 12 (9) ◽  
pp. 1449
Author(s):  
Elahe Akbari ◽  
Ali Darvishi Boloorani ◽  
Najmeh Neysani Samany ◽  
Saeid Hamzeh ◽  
Saeid Soufizadeh ◽  
...  
Keyword(s):  
Feature Selection ◽  
Particle Swarm Optimization ◽  
Importance Measure ◽  
Swarm Optimization ◽  
Feature Sets ◽  
Classification Feature ◽  
Spectral Bands ◽  
Multi Temporal ◽  
Crop Mapping ◽  
Sentinel 2

Timely and accurate information on crop mapping and monitoring is necessary for agricultural resources management. Accordingly, the applicability of the proposed classification-feature selection ensemble procedure with different feature sets for crop mapping is investigated. Here, we produced various feature sets including spectral bands, spectral indices, variation of spectral index, texture, and combinations of features to map different types of crops. By using various feature sets and the random forest (RF) classifier, the crop maps were created. In aiming to determine the most relevant and distinctive features, the particle swarm optimization (PSO) and RF-variable importance measure feature selection methods were examined. The classification-feature selection ensemble procedure was adapted to combine the outputs of different feature sets from the better feature selection method using majority votes. Multi-temporal Sentinel-2 data has been used in Ghale-Nou county of Tehran, Iran. The performance of RF was efficient in crop mapping especially by spectral bands and texture in combination with other feature sets. Our results showed that the PSO-based feature selection leads to a more accurate classification than the RF-variable importance measure, in almost all feature sets for all crop types. The RF classifier-PSO ensemble procedure for crop mapping outperformed the RF classifier in each feature set with regard to the class-wise and overall accuracies (OA) (of about 2.7–7.4% increases in OA and 0.48–3.68% (silage maize), 0–1.61% (rice), 2.82–15.43% (alfalfa), and 10.96–41.13% (vegetables) improvement in F-scores for all feature sets). The proposed method could mainly be useful to differentiate between heterogeneous crop fields (e.g., vegetables in this study) due to their more obtained omission/commission errors reduction.

scholarly journals ASSESSMENT OF THE GEOMETRIC QUALITY OF SENTINEL-2 DATA

2016 ◽  
Vol XLI-B1 ◽  
pp. 489-494 ◽  
Author(s):  
M. Pandžic ◽  
D. Mihajlovic ◽  
J. Pandžic ◽  
N. Pfeifer
Keyword(s):  
Visual Analysis ◽  
High Reliability ◽  
European Space Agency ◽  
Statistical Parameter ◽  
Quality Analysis ◽  
Line Segments ◽  
Total Length ◽  
Space Agency ◽  
New Perspective ◽  
Sentinel 2

High resolution (10 m and 20 m) optical imagery satellite Sentinel-2 brings a new perspective to Earth observation. Its frequent revisit time enables monitoring the Earth surface with high reliability. Since Sentinel-2 data is provided free of charge by the European Space Agency, its mass use for variety of purposes is expected. Quality evaluation of Sentinel-2 data is thus necessary. Quality analysis in this experiment is based on comparison of Sentinel-2 imagery with reference data (orthophoto). From the possible set of features to compare (point features, texture lines, objects, etc.) line segments were chosen because visual analysis suggested that scale differences matter least for these features. The experiment was thus designed to compare long line segments (e.g. airstrips, roads, etc.) in both datasets as the most representative entities. Edge detection was applied to both images and corresponding edges were manually selected. The statistical parameter which describes the geometrical relation between different images (and between datasets in general) covering the same area is calculated as the distance between corresponding curves in two datasets. The experiment was conducted for two different test sites, Austria and Serbia. From 21 lines with a total length of ca. 120 km the average offset of 6.031 m (0.60 pixel of Sentinel-2) was obtained for Austria, whereas for Serbia the average offset of 12.720 m (1.27 pixel of Sentinel-2) was obtained out of 10 lines with a total length of ca. 38 km.

Sign in / Sign up

Export Citation Format

Share Document