HyperField, a constellation of polar sun-synchronous nanosatellites, is being developed by the
Finnish company Kuva Space. The constellation that will be launched in 2023 consists of 100
CubeSats with hyperspectral systems operating in the visible to near-infrared (VIS-NIR,
450-1100 nm) or Visible-to-shortwave infrared (VIS-SWIR, 450-2500 nm) ranges and provides
two to three times daily images of every location on Earth.
This paper presents the first and second generations of the Hyperfield satellites. It reviews along with their innovative platform and detector technology, the optical modes, planned mission operations, advanced AI-based processing architecture and novel algorithms are developed to improve the acquisition, enhance the image quality and produce tailored-based services.
Search and Rescue (SAR) operations following natural or anthropogenic disasters are often hindered by smoke, rain, fog and haze. Developing methods that combat Degraded Visual Environments (DVE) and ensure the rapid detection of survivors and rescue personnel after a disaster is crucial to reducing mortality.
This paper proposes a novel AI scheme to detect static and moving objects using snapshot NIR hyperspectral data. The proposed model leverages spatial features through object detection to identify objects and, at the same time, applies a semantic segmentation algorithm based on spectral features to validate the presence of firefighters within the detected bounding boxes. The training is optimised for real-time high-performance inference by exporting it to TensorRT. This approach has been successfully demonstrated in various realistic scenarios with an F1-score of 0.923 and 77.9 frames per second.
This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although a significant increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.
Soil differential settlements that cause structural damage to heritage buildings are precipitating cultural and economic
value losses. Adequate damage assessment as well as protection and preservation of the built patrimony are priorities at
national and local levels, so they require advanced integration and analysis of environmental, architectural and historical
parameters. The GEPATAR project (GEotechnical and Patrimonial Archives Toolbox for ARchitectural conservation in
Belgium) aims to create an online interactive geo-information tool that allows the user to view and to be informed about
the Belgian heritage buildings at risk due to differential soil settlements.
Multi-temporal interferometry techniques (MTI) have been proven to be a powerful technique for analyzing earth surface
deformation patterns through time series of Synthetic Aperture Radar (SAR) images. These techniques allow to measure
ground movements over wide areas at high precision and relatively low cost. In this project, Persistent Scatterer Synthetic
Aperture Radar Interferometry (PS-InSAR) and Multidimensional Small Baseline Subsets (MSBAS) are used to measure
and monitor the temporal evolution of surface deformations across Belgium.
This information is integrated with the Belgian heritage data by means of an interactive toolbox in a GIS environment in
order to identify the level of risk. At country scale, the toolbox includes ground deformation hazard maps, geological
information, location of patrimony buildings and land use; while at local scale, it includes settlement rates, photographic
and historical surveys as well as architectural and geotechnical information. Some case studies are investigated by means
of on-site monitoring techniques and stability analysis to evaluate the applied approaches.
This paper presents a description of the methodology being implemented in the project together with the case study of the
Saint Vincent’s church which is located on a former colliery zone. For this building, damage is assessed by means of PSInSAR.
KEYWORDS: 3D modeling, Thermal modeling, Data modeling, Hyperspectral imaging, Statistical analysis, Buildings, RGB color model, Temperature metrology, Sun, Image classification
Land Surface Temperature (LST) and Land Surface Emissivity (LSE) are commonly retrieved from thermal hyperspectral imaging. However, their retrieval is not a straightforward procedure because the mathematical problem is ill-posed. This procedure becomes more challenging in an urban area where the spatial distribution of temperature varies substantially in space and time. For assessing the influence of several spatial variances on the deviation of the temperature in the scene, a statistical model is created. The model was tested using several images from various times in the day and was validated using in-situ measurements. The results highlight the importance of the geometry of the scene and its setting relative to the position of the sun during day time. It also shows that when the position of the sun is in zenith, the main contribution to the thermal distribution in the scene is the thermal capacity of the landcover materials. In this paper we propose a new Temperature and Emissivity Separation (TES) method which integrates 3D surface and landcover information from LIDAR and VNIR hyperspectral imaging data in an attempt to improve the TES procedure for a thermal hyperspectral scene. The experimental results prove the high accuracy of the proposed method in comparison to another conventional TES model.
Military operations in urban areas became more relevant in the past decades. Detailed situation awareness in these complex environments is crucial for successful operations. Within the EDA (European Defence Agency) project on “Detection in Urban scenario using Combined Airborne imaging Sensors” (DUCAS) an extensive data set of hyperspectral and high spatial resolution data as well as three dimensional (3D) laser data was generated in a common field trial in the city of Zeebrugge, Belgium, in the year 2011. In the frame of DUCAS, methods were developed at two levels of processing. In the first level, single sensor data were used for land cover mapping and the detection of targets of interest (i.e. personnel, vehicles and objects). In the second level, data fusion was applied at pixel level as well as information level to investigate the benefits of combining sensor systems in an operational context. Providing data for mission planning and mapping is an important task for aerial reconnaissance and it includes the creation or the update of high quality 2D and 3D maps. In DUCAS, semi-automatic methods and a wide range of sensor data (hyperspectral, LIDAR, high resolution orthophotos and video data) were used for the creation of highly detailed land cover maps as well as urban terrain models. Combining the diverse information gained by different sensors increases the information content and the quality of the extracted information. In this paper we will present advanced methods for the creation of 2D/3D maps, show results and the benefit of fusing multi-sensor data.
Seven countries within the European Defence Agency (EDA) framework are joining effort in a four year project (2009-2013) on Detection in Urban scenario using Combined Airborne imaging Sensors (DUCAS). Data has been collected in a joint field trial including instrumentation for 3D mapping, hyperspectral and high resolution imagery together with in situ instrumentation for target, background and atmospheric characterization. Extensive analysis with respect to detection and classification has been performed. Progress in performance has been shown using combinations of hyperspectral and high spatial resolution sensors.
Very high resolution multispectral imaging reached a high level of reliability and accuracy for target detection and
classification. However, in an urban scene, the complexity is raised, making the detection and the identification of small
objects difficult. One way to overcome this difficulty is to combine spectral information with 3D data. A set of (very
high resolution) airborne multispectral image sequences was acquired over the urban area of Zeebrugge, Belgium. The
data consist of three bands in the visible (VIS) region, one band in the near infrared (NIR) range and two bands in the
mid-wave infrared (MWIR) region. Images are obtained images at a frame rate of 1/2 frame per second for the VIS and
NIR image and 2 frames per second for the MWIR bands. The sensors have a decimetric spatial resolution. The
combination of frame rate with flight altitude and speed results in a large overlap between successive images. The
current paper proposes a scheme to combine 3D information from along-track stereo, exploiting the overlap between
images on one hand and spectral information on the other hand for unsupervised detection of targets. For the extraction
of 3D information, the disparity map between different image pairs is determined automatically using an MRF-based
method. For the unsupervised target detection, an anomaly detection algorithm is applied. Different methods for inserting
the obtained 3D information into the target detection scheme are discussed.
The EDA project "Detection in Urban scenario using Combined Airborne imaging Sensors" (DUCAS) is in progress.
The aim of the project is to investigate the potential benefit of combined high spatial and spectral resolution airborne
imagery for several defense applications in the urban area. The project is taking advantage of the combined resources
from 7 contributing nations within the EDA framework. An extensive field trial has been carried out in the city of
Zeebrugge at the Belgian coast in June 2011. The Belgian armed forces contributed with platforms, weapons, personnel
(soldiers) and logistics for the trial. Ground truth measurements with respect to geometrical characteristics, optical
material properties and weather conditions were obtained in addition to hyperspectral, multispectral and high resolution
spatial imagery.
High spectral/spatial resolution sensor data are used for detection, classification, identification and tracking.
Since the launch of Terrasar-X, Radarsat 2 and the Cosmo-Skymed constellation, spaceborne SAR data with
a high spatial resolution have become more readily available, allowing to monitor areas with a high level of
human activity independent of weather circumstances. The current paper investigates the use of such data for
geospatial intelligence applications in an harbor environment. The applications of interest are change detection
and activity monitoring. For the analysis a set of more than twenty datasets from the three above mentioned
satellite systems, acquired over a period of 30 days over the sea harbor of Zeebrugge in Belgium is available.
Most datasets are high-resolution spotlight mode, but some scansar and full-polarimetric data have also been
acquired. In the current paper HiRes spotlight data from the Cosmo-Skymed constellation are used for change
detection and activity monitoring in the port.
Urban areas are rapidly changing all over the world and therefore provoke the necessity to update urban maps frequently.
Remote sensing has been used for many years to monitor these changes. The urban scene is characterized by a very high
complexity, containing objects formed from different types of man-made materials as well as natural vegetation.
Hyperspectral sensors provide the capability to map the surface materials present in the scene using their spectra and
therefore to identify the main object classes in the scene in a relatively easy manner. However ambiguities persist where
different types of objects are constructed of the same material. This is for instance the case for roads and roof covers.
Although higher-level image processing (e.g. spatial reasoning) might be able to relief some of these constraints, this
task is far from straight forward. In the current paper the authors fused information gathered using a hyperspectral sensor
with that of high-resolution polarimetric SAR data. SAR data give information about the type of scattering backscatter
from an object in the scene, its geometry and its dielectric properties. Therefore, the information obtained using the SAR
processing is complementary to that obtained using hyperspectral data. This research was applied on a dataset consisting
of hyperspectral data from the HyMAP sensor (126 channels in VIS-SWIR) and E-SAR data which consists of fullpolarimetric
L-band and dual-polarisation (HH and VV) X-band data. Two supervised classifications are used; 'Logistic
Regression' (LR) which applied to the SAR and the PolSAR data and a 'Matched Filter' which is applied to the
hyperspectral data. The results of the classification are fused in order to improve the mapping of the main classes in the
scene and were compared to a ground truth map that was constructed by combining a digital topographic map and a
vectorized cadastral map of the research area. An adequate change detection of man-made objects in urban scenes was
obtained by the fusion of features derived from SAR, PolSAR and hyperspectral data.
The coastal zone is an extremely dynamic system. Variations in the concentration of its major constituents occur rapidly
over space and time. This is in response to changes in bathymetry and tidal forces coupled with the influences of fronts,
upwelling zones and river inflow. Today's research on the functioning of estuarine and coastal ecosystems, as well as
attempts to quantify some of their biogeochemical fluxes are based on highly time consuming and costly sea campaigns
and laboratory analyses.
On September 2002, an airborne campaign using CASI sensor covered part of the Scheldt estuary (Belgium-
Netherlands coastal zone). A 13 sampling stations field survey was realised in order to cover as quickly as possible the
wide range of water quality encountered from the mouth of the estuary to the outer limit of the plume. Correlation was
searched between classical ground truth measurements and the rich information provided by numerous CASI-SWIR
spectral bands carefully chosen. These relations were not sufficient enough to derive synoptic view of the spatial
distribution of many biogeochemical parameters in the Scheldt estuary and plume.
In this research we found that some biogeochemical parameters of interest in estuaries and plumes that were retrieved
using imaging spectroscopy techniques as the MF (Matched filtering) and the MTMF (Mixture Tuned Matched
Filtering) are very encouraging. We showed that using those spectra based processing techniques we could accurately
obtained the concentration distribution of suspended particulate matter (SPM) and particulate organic matter (POM),
that we could not retrieved using the classical statistical techniques. Moreover, using the imaging spectroscopy
techniques we significantly improved the coloured dissolved organic matter (CDOM) concentration classification,
relatively to the results derived using the multiple regression technique.
This paper describes a new method for classification of hyperspectral images for extracting carthographic objects. The developed method is intended as a tool for automatic map updating. The idea is to use an existing map of the region of interest as a learning set. The proposed method is based on logistic regression. Logistic regression (LR) is a supervised multi-variate statistical tool that finds an optimal combination of the input channels for distinguishing one class from all the others. LR thus results in detection images per class. These can be combined into a classification image. The LR method that is used here is a step-wise optimisation that also performs a channel selection. The results of the LR are further improved by taking into account spatial information by means of a region growing method. The parameters of the region growing are optimised for each class of interest. For each class the optimal set of parameters is determined. The method is applied on a HyMap hyperspectral image of an area in Southern Germany and the results are compared to those of classical methods. For the comparison a ground truth image was created by combining data from a cadaster map and a digital topographic map.
For hydrology and terrestrial ecosystem studies, topography has a significant influence on the amount of intercepted solar radiation, the surface and sub-surface water movements, the type and distribution of vegetation and the microclimate. Processing Digital Elevation Model (DEM) data to extract hydrological features becomes a routine, but the numerous DEMs available stress the importance of their quality assessment. Radar interferometry (InSAR) technique is a promising approach to generate digital elevation models. The goal of this research is to verify to what extend the InSAR DEM can be used as a topographic database for deriving hydrological informations. This study was realised over the Dendre and the Lesse watersheds. Because DEM quality cannot be determined by a single criterion, the quality assessment should be application oriented. In this study, the NGI (National Geographic Institute of Belgium) DEM was chosen as a topographic reference for the quality assessment of the InSAR DEMs. The Root Mean Square (RMS) of the altitude difference between the NGI and the InSAR DEM was used as general quality measurement. The mean slope value has been calculated to characterise the relief of the basin. For both of the basins, watershed borders and hydrographic network were generated with GIS technique. The results obtained were compared between them and with digitised hydrographic network. Hydrographic network derived from InSAR DEM was not found accurate enough in flat wide valley. For the studied areas, the InSAR DEMs are precise enough for large-scale hydrological investigation where information like watershed border or relief is needed. However, InSAR DEMs is not suitable for hydraulic models, because they require extreme accuracy.
A several kilometres thick sequence of mostly marine salt with inter-bedded gypsum, shale and dolomite rock of Pliocene to Pleistocene age build several salt diapirs in the Dead Sea area. The Lisan Peninsula salt diapir is elongated in the N-S direction, and includes several sub-domes and a structural depression. Differential interferograms were generated for several time intervals of seven to ninety three months between 1992 and 1999 and show a large diversity of uplift and subsidence features in the peninsula. The uplift rate, which has been measured, is in correspondence to the geological rate evaluated by other geological researches. The subsidence, mainly in the south dome and the cape are much more significant. Inversion deformation in the cape between the year 1995-1996 suggested to be linked to the 22 November 1995 Nuweiba earthquake. This paper suggested a tectonic mechanism connecting the salt deformation in the Lisan Peninsula with the activity of Boqeq fault.
The Dead Sea is very harsh environment even for microorganisms adapted to hypersaline environment. Not only does the Dead Sea contain the highest salt concentration of all natural lakes inhabited by living organisms, but the peculiar ionic composition of its water, with its high concentration of divalent cations magnesium and calcium, is highly inhibitory even to those microorganisms that are the most adapted to life in the sea. In this research imaging spectroscopy and microbiological studied used to investigate the spatial distribution of various Archaea populations according to the salty saturation of Mor swamp, Dead Sea Basin. Data from the DLR airborne sensor DAIS-7915 in the spectral range between 0.4 to 2.4 micrometers were acquired along with field and laboratory spectral measurements. The spatial and spectral data were completed by microbiological analysis. The spectral information helped to detect a concentric distribution of the Archaea population, which seems linked to the state of the salty substrate. In the wet muddy central zone lives an Archaea with the relatively lowest salt tolerance. From this centre to the peripheries, the tolerance to salt of the Archaea population was found to be increasing, as the substation changes from salty pools to salty muds and finally to massive salt layers.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.