The Collaborative Representation-based Detector (CRD) performs anomaly detection for hyperspectral data using a linear representation of local neighbors for background estimation, which may not fully capture the informational content and spectral variability in complex hyperspectral images with heterogenous background. To deal with this aspect, the Collaborative Representation-based Attention Network (CRAN) is introduced in this letter, providing a nonlinear representation of data samples for background estimation. Both local neighbors and global samples are used in parallel, and their outputs are fused through a cross-attention mechanism. Experimental results show a good performance of CRAN in comparison with several state-of-the-art anomaly detectors.

Unlike hard classification from medium-resolution sensors, spectral unmixing at sub-pixel level offers improved accuracy in estimating the total surface occupied by a material of interest within a given area. While in ideal cases imaging spectrometer data should be utilized for this purpose, we propose to use a limited number of fixed classes in order to perform spectral unmixing from multispectral data to address the specific challenge of estimating the surface area covered by floating plastic debris in inland waters. In that context, working with multispectral data is motivated by extended opportunities to identify and monitor narrow water channels for variable plastic appearances, in terms of extended coverage, spatial and temporal resolution.

This paper provides insights into invasive Quagga mussel proliferation on the bottom of lakes around the Alps, considering potential threats to submerged cultural heritage sites such as Les Argilliez in lake Neuchâtel. By observing typical spectral characteristics of mussels and other water constituents and benthic materials, we report that this phenomenon could be observed in shallow waters and monitored over time using Earth Observation data. Preliminary results using Sentinel-2 data, partially validated through underwater surveys, indicate that the detection of these changes should rely on differences in the green portion of the spectrum.

On August 2024, the DLR Earth Sensing Imaging Spectrometer (DESIS) completed six years of operations onboard the International Space Station (ISS). In that time, DESIS has acquired data worldwide for both scientific and commercial users. The continuously growing data archive supports methodical and application developments for the monitoring of the Earth’s surface. We present a short update of the mission status and then provide a deeper view into the DESIS data archive. DESIS is currently operating in nominal conditions, further expanding its multitemporal data archive, which holds great value for a wide range of applications and serves as a database for recent and upcoming hyperspectral Earth-observing missions. It enables long-term analysis of physical phenomena and land use changes by providing high-resolution data spanning an extended temporal range for the monitoring of a site of interest.

In this paper we present a combined approach on estimating the endangerment of cultural heritage sites getting struck by strong rain events and flash floods. As shown in the UN Report on “Human Costs of Disasters” from 2020 [1] flood events show a far above average increase by 130 % from the decades 1980 to 1999 compared to 2000 to 2019 where most other disaster types like landslides, storms or wildfires show only an average increase of about 20 to 50 %. These insights together with the increase of flash floods originating from stationary rain in Germany caused the intensification of our research on danger analysis from strong rain events – especially for cultural heritage sites. In this paper we present different approaches deriving flood dangers, including local terrain modeling and water runoff simulation, and how to combine them to produce a concise estimation of the flood risk for cultural heritage sites, which can directly be used by the responsible authorities. The methods are applied to different cultural heritage sites in Europe, and results are discussed.

Over the years, space-based remote sensing of nighttime light has mostly utilized panchromatic or multispectral sensors. The hyperspectral mission EnMAP, primarily intended for daytime observations, can also produce hyperspectral data of nighttime lighting. EnMAP data from the Las Vegas Strip was analyzed by detecting locations of certain lighting types using matched filtering and detection of sharp emission spikes at known wavelengths. Additionally, images from different nights were compared to determine how changes in observation geometry affect the observed spectra. The results indicate that corrections for geometric effects would be necessary to produce robust time-series data. The EnMAP data were also used to approximate two in-dices related to the efficiency and spectral quality of the light, the luminous efficiency of radiation (LER) and the spectral G index. Future developments will include ana-lyzing scenes from other cities using similar approaches. Program code used in this work is available at https://github.com/silmae/EnMAP_nightlights.

The DLR HyperSpectral Unmixing (DLR HySU) open benchmark dataset includes airborne hyperspectral and RGB imagery of targets of different materials and sizes on a homogeneous background, complemented by simultaneous ground-based reflectance measurements. The dataset allows assessing dimensionality estimation, endmember extraction with and without pure pixel assumption, and abundance estimation in the frame of spectral unmixing applications, enabling estimations at sub-pixel level. This paper presents the first works in the literature using the dataset, which demonstrate that DLR HySU is filling a gap regarding validation using real imaging spectrometer data with accurately measured targets.

Current shadow-aware hyperspectral unmixing methods often suffer from noisy abundance maps and inaccurate abundance estimation of shadowed pixels, as these are characterized by low reflectance values and signal-to-noise ratio. In order to achieve a shadow-insensitive abundance estimation, in this article we propose a novel spatial-spectral shadow-aware mixing model (S3AM). The approach models shadows by considering diffuse solar illumination and secondary illumination from neighbouring pixels. Besides, spatial regularization using shadow-aware weighted Total Variation is employed. Specifically, pixels in the local neighborhood of a target pixel take simultaneously into account spectral similarity measures derived from the imagery, elevation similarity measures derived from a Digital Surface Model, and the impact of shadows. The sky view factorF, needed as input for the model, is also derived from available Digital Surface Models (DSM). The proposed approach is extensively validated and compared to state-of-the-art methods on two datasets. Results demonstrate that S3AM yields superior abundance estimation maps for real scenarios, by decreasing the noise in the results and achieving more accurate reconstructions in the presence of shadows.

The DLR Earth Sensing Spectrometer (DESIS) on board the International Space Station (ISS) has been providing high quality hyperspectral data to the scientific community and commercial users since the start of operations in September 2018. After almost 4 years in orbit, the DESIS instrument continues to operate correctly and to deliver hyperspectral data products for a wide variety of applications. In order to support this successful activity, the calibration team regularly analyzes the instrument data and provides updates using vicarious calibration. We present here the latest results from the DES IS vicarious calibration and our plans for future improvements.

The DLR Earth Sensing Imaging Spectrometer (DESIS) [1] is a spaceborne instrument installed and operated on the International Space Station (ISS). The German Aerospace Center (DLR) has developed the instrument and the software for data processing [2], while the US company Teledyne Brown Engineering (TBE) provided the Multi-User System for Earth Sensing (MUSES) platform, where DESIS is installed, and the infrastructure for operations and data tasking [3]. The main parameters of the DESIS instrument are summarized in Table 1. DESIS is equipped with an on-board calibration unit and a rotating pointing mirror (POI). The POI can change the line of sight ±15° in the forward/backward direction (independently of the MUSES orientation), allowing BRDF measurements of the same area on ground within an overflight.

The DLR Earth Sensing Spectrometer (DESIS) on board the International Space Station (ISS) is an imaging spectrometer for remote sensing developed by the German Aerospace Center (DLR) and operated by Teledyne Brown Engineering (TBE). In order to maintain the quality of the data during the operational phase, the calibration team monitors the calibration parameters and updates them when a significant deviation is found. The update of calibration parameters is based on vicarious calibration using Earth scenes over uniform areas and RadCalNet calibration sites. We present here a description of the calibration techniques used for the DESIS instrument with special emphasis on the vicarious calibration.

The DLR Earth Sensing Imaging Spectrometer (DESIS) is a space-based instrument installed and operated on the International Space Station (ISS) [1]. This space mission is the achievement of the collaboration between the German Aerospace Center (DLR) and the US company Teledyne Brown Engineering (TBE). DLR has developed the instrument and the software for data processing [2], while TBE provides the Multi-User System for Earth Sensing (MUSES) platform, where DESIS is installed, and the infrastructure for operation and data tasking [3].

This paper describes the contribution of the DLR team ranking 3rdin Track 1 of the 2020 IEEE GRSS Data Fusion Contest, with results ranking 2ndin Track 2 of the same contest being reported in a companion paper. The classifications are based on refinements of low-resolution MODIS labeling using available higher resolution Sentinel-1 and Sentinel-2 data. Results are initialized with a handcrafted decision tree integrating output from a random forest classifier, and subsequently boosted by detectors for specific classes.

This paper describes the contribution of the DLR team ranking 2ndin Track 2 of the 2020 IEEE GRSS Data Fusion Contest. The semantic classification of multimodal earth observation data proposed is based on the refinement of low-resolution MODIS labels, using as auxiliary training data higher resolution labels available for a validation data set. The classification is initialized with a handcrafted decision tree integrating output from a random forest classifier, and subsequently boosted by detectors for specific classes. The results of the team ranking 3rdin Track 1 of the same contest are reported in a companion paper.

Imaging spectrometry provides densely sampled and finely structured spectral information for each image pixel over large areas, enabling the characterization of materials on the Earth's surface by measuring and analyzing quantitative parameters allowing the user to identify and characterize Earth surface materials such as minerals in rocks and soils, vegetation types and stress indicators, and water constituents. The recently launched DLR Earth Sensing Imaging Spectrometer (DESIS) installed on the International Space Station (ISS) closes the long-term gap of sparsely available spaceborne imaging spectrometry data and will be part of the upcoming fleet of such new instruments in orbit. DESIS measures in the spectral range from 400 and 1000 nm with a spectral sampling distance of 2.55 nm and a Full Width Half Maximum (FWHM) of about 3.5 nm. The various DESIS data products available for users are described with the focus on specific processing steps. A summary of the data quality results are given. The product validation studies show that top-of-atmosphere radiance, geometrically corrected, and bottom-of-atmosphere reflectance products meet the mission requirements.

This paper presents a shadow restoration method based on the nonlinear mixture model. A shadowed spectrum is modeled by using a pure sunlit spectrum for the same material following physical assumptions. Regarding pure sunlit and shadowed spectra as endmembers, an unmixing process is then conducted pixel-wise using a nonlinear mixture model. Shadow pixels are restored by simulating their exposure to sunlight through a combination of selected sunlit endmembers spectra, weighted by abundance values. Experiments conducted on a real airborne hyperspectral image are evaluated through spectra comparison and classification. In addition, a soft shadow map is generated, which quantifies the shadow intensity at the edges between sunlit and shadow areas.

DESIS (DLR Earth Sensing Imaging Spectrometer) is a space-based hyperspectral sensor currently installed and operated in the International Space Station (ISS). The instrument is the result of the collaboration between the German Aerospace Center (DLR) and Teledyne Brown Engineering (TBE). DLR has developed the instrument and the software for data processing, while TBE provides the Multi-User System for Earth Sensing (MUSES), where DESIS is installed, and the infrastructure for operation.

This paper describes the winning contribution to the 2019 IEEE GRSS Data Fusion Contest Multi-view Semantic Stereo Challenge. In this challenge, a digital surface model (DSM) and a semantic segmentation should be derived from a large number of multi-spectral WorldView-3 images. Results from 50 stereo pairs matched using Semi-Global Matching (SGM) are fused into a DSM. Semantic segmentation is performed with an ensemble of FCN networks taking as input RGB, multi-spectral and height data. Their results are then merged with pixel-wise detectors for the classes water and high vegetation. Compared to the second and third placed teams (mIOU-3 scores of 0.73 and 0.7295), our contribution reached a significantly higher score of 0.745.

This article describes the workflow of the classification algorithm which ranked at 2ndplace in the 2018 GRSS Data Fusion Contest. The objective of the contest was to provide a classification map with 20 classes on a complex urban scenario. The available multi-modal data were acquired from hyperspectral, LiDAR and very high-resolution RGB sensors flown on the same platform over the city of Houston, TX, USA. The classification was obtained by merging deep convolutional and shallow fully-connected neural networks on a simplified set of classes, complemented by a series of specific detectors and ad hoc classifiers.

The German Aerospace Center (DLR) and Teledyne Brown Engineering (TBE), located in Huntsville, Alabama, USA, cooperate to develop and operate the new space-based hyperspectral sensor DLR Earth Sensing Imaging Spectrometer (DESIS). While TBE provides the Multi-User platform MUSES and infrastructure for operation of the DESIS instrument on the ISS, DLR is responsible for providing the instrument and the processing software as well as instrument in-flight calibration and product quality operations. MUSES has been already launched and installed on the International Space Station ISS in early 2017 and DESIS will follow mid of 2018. We present here an overview of the DESIS instrument, the on-ground data processing, the in-flight calibration and product quality investigations.

Unmixing-based Denoising exploits spectral unmixing results to selectively recover bands affected by a low Signal-to-Noise Ratio in hypespectral images. This paper proposes to apply this algorithm, which operates pixelwise, for the inpainting of corrupted pixels and the removal of drop-out artifacts in hy-perspectral scenes. The reported experiments are characterized by a low reconstruction error for the reconstructed spectra and a high visual quality of the processed images, and outperform state of the art methods in terms of reconstruction error.

Spectral unmixing and denoising of hyperspectral images have always been regarded as separate problems. By considering the physical properties of a mixed spectrum, this letter introduces unmixing-based denoising, a supervised methodology representing any pixel as a linear combination of reference spectra in a hyperspectral scene. Such spectra are related to some classes of interest, and exhibit negligible noise influences, as they are averaged over areas for which ground truth is available. After the unmixing process, the residual vector is mostly composed by the contributions of uninteresting materials, unwanted atmospheric influences and sensor-induced noise, and is thus ignored in the reconstruction of each spectrum. The proposed method, in spite of its simplicity, is able to remove noise effectively for spectral bands with both low and high signal-to-noise ratio. Experiments show that this method could be used to retrieve spectral information from corrupted bands, such as the ones placed at the edge between ultraviolet and visible light frequencies, which are usually discarded in practical applications. The proposed method achieves better results in terms of visual quality in comparison to competitors, if the mean squared error is kept constant. This leads to questioning the validity of mean squared error as a predictor for image quality in remote sensing applications.

This paper presents a classification methodology for hyperspectral data based on synergetics theory. Pattern recognition algorithms based on synergetics have been applied to images in the spatial domain with limited success in the past, given their dependence on the rotation, shifting, and scaling of the images. These drawbacks can be discarded if such methods are applied to data acquired by a hyperspectral sensor in the spectral domain, as each single spectrum, related to an image element in the hyperspectral scene, can be analyzed independently. The spectrum is first projected in a space spanned by a set of user-defined prototype vectors, which belong to some classes of interest, and then attracted by a final state associated to a prototype. The spectrum can thus be classified, establishing a first attempt at performing a pixel-wise image classification using notions derived from synergetics. As typical synergetics-based systems have the drawback of a rigid training step, we introduce a new procedure which allows the selection of a training area for each class of interest, used to weight the prototype vectors through attention parameters and to produce a more accurate classification map through plurality vote of independent classifications. As each classification is in principle obtained on the basis of a single training sample per class, the proposed technique could be particularly effective in tasks where only a small training data set is available. The results presented are promising and often outperform state-of-the-art classification methodologies, both general and specific to hyperspectral data.

This paper presents a quasi-unsupervised methodology to detect endmembers within an hyperspectral scene and to derive a pixel-wise classification on its basis. The endmember detection step takes as input an overcomplete spectral library, and detects the materials within a scene by analyzing derivative features under the sparsity assumption. The purest pixels for each detected material are then fed to a classifier based on synergetics theory, which is able to produce accurate classification maps on the basis of a restricted training dataset. As the classifier projects the image onto a subspace composed by the classes of interest found in the first step, a focused dimensionality reduction is performed in which every dimension is semantically meaningful.

This work presents a new approximation for the Kolmogorov complexity of strings based on compression with smallest Context Free Grammars (CFG). If, for a given string, a dictionary containing its relevant patterns may be regarded as a model, a Context-Free Grammar may represent a generative model, with all of its rules (and as a consequence its own size) being meaningful. Thus, we define a new complexity approximation which takes into account the size of the string model, in a representation similar to the Minimum Description Length. These considerations result in the definition of a new compression-based similarity measure: its novelty lies in the fact that the impact of complexity overestimations, due to the limits that a real compressor has, can be accounted for and decreased.

Earth observation image-understanding methodologies may be hindered by the assumed data models and the estimated parameters on which they are often heavily dependent. First, the definition of the parameters may negatively affect the quality of the analysis. The parameters could not be captured in all aspects, and those resulting superfluous or not accurately tuned may introduce nuisance in the data. Furthermore, the diversity of the data, as regards sensor type, spatial, spectral, and radiometric resolution, and the variety and regularity of the observed scenes make it difficult to establish enough valid and robust statistical models to describe them. This letter proposes algorithmic information theory-based analysis as a valid solution to overcome these limitations. We will present different applications on satellite images, i.e., clustering, classification, artifact detection, and image time series mining, showing the generalization power of these parameter-free data-driven methods based on the computational complexity analysis.

Information content and compression are tightly related concepts that can be addressed by classical and algorithmic information theory. Several entities in the latter have been defined relying upon notions of the former, such as entropy and mutual information, since the basic concepts of these two approaches present many common tracts. In this work we further expand this parallelism by defining the algorithmic versions of cross-entropy and relative entropy (or Kullback-Leiblerdivergence), two well-known concepts in classical information theory. We define the cross-complexity of an object x with respect to another object y as the amount of computational resources needed to specify x in terms of y, and the complexity of x related to y as the compression power which is lost when using such a description for x, with respect to its shortest representation. Since the main drawback of these concepts is their uncomputability, a suitable approximation based on data compression is derived for both and applied to real data. This allows us to improve the results obtained by similar previous methods which were intuitively defined.

Many fawns and other wild animals are killed by mowing machines every year. To prevent them from being killed or injured, a sensor system is being developed to detect the fawns hidden in meadows under mowing. Beside a microwave radar system, two cameras (thermal infrared and RGB) take a picture at the mower's current location. This contribution focuses on the compression-based algorithm that will be adopted to detect the locations containing a fawn hiding in the grass: such approach, being parameter-free, allows performing a fully unsupervised clustering by exploiting the intrinsic properties of data compression to estimate the amount of shared information between two images.

High resolution remote sensing SAR images — such as the image data acquired by the German TerraSAR-X mission — contain a variety of details that have to be extracted by automated processing in order to fully exploit and understand the image content. In particular, the interpretation of man-made structures that are typical of built-up or agricultural areas poses a number of challenges including parameterized image focusing during routine processing, careful despeckling, descriptor and feature extraction, and final classification including specific scattering and 3D effects. Therefore, we propose a set of general sequential as well as dedicated application-dependent processing steps that allow user-oriented classification of high resolution SAR images. We will also report on actual classification results and experiences.

Many methodologies and similarity measures based on data compression have been recently introduced to compute similarities between general kinds of data. Two important similarity indices are the normalized information distance (NID), with its approximation normalized compression distance (NCD), and the pattern recognition based on data compression (PRDC). At first sight NCD and PRDC are quite different: the former is a direct metric while the latter is a methodology which computes a compression distance with an intermediate step of encoding files into texts. In spite of this, it is possible to demonstrate that they are both based on estimates of Kolmogorov complexities (when this is known for the former but not for the latter). Finally, this results in the definition of a new measure: the model conditioned data compression based similarity measure (McDCSM), which is a modified version of PRDC, and is the topic of this paper.

This paper proposes complexity based analysis as a valid alternative to classic image analysis methodologies for Earth Observation imagery, which are heavily dependant on the assumed data models. These methods are totally model-free and data-driven, and may be successfully employed for image classification and indexing, regardless of spatial and radiometric resolution of the scene and sensor type.

While typical remote sensing imaging instruments produce more and more data, what we miss today are reliable tools for automated information extraction form these images. In the following, we propose a so-called Content Map, a novel Earth Observation value adding product. Basically, it comprises several class files and a viewer showing the different classes of land use and objects contained in the corresponding image data. In order to avoid processing delays, the class files have to be generated in an unsupervised mode as a real time product; thus, interactive user interactions have to be limited to training and testing intervals. As typical examples we use image data of the German TerraSAR-X mission that produces SAR image data in a variety of different modes.