Reflectance composites that capture bare soil pixels from multispectral image data are increasingly being analysed to model soil constituents such as soil organic carbon. These temporal composites are used instead of single-date multispectral images to account for the frequent vegetation cover of soils and, thus, to get broader spatial coverage of bare soil pixels. Most soil compositing techniques require thresholds derived from spectral indices such as the Normalised Difference Vegetation Index (NDVI) and the Normalised Burn Ratio 2 (NBR2) to separate bare soils from all other land cover types. However, the threshold derivation is handled based on expert knowledge of a specific area, statistical percentile definitions or in situ data. For operational processors, such site-specific and partly manual strategies are not applicable. There is a need for a more generic solution to derive thresholds for large-scale processing without manual intervention. This study presents a novel HIstogram SEparation Threshold (HISET) methodology deriving spectral index thresholds and testing them for a Sentinel-2 temporal data stack. The technique is spectral index-independent, data-driven and can be evaluated based on a quality score. We tested HISET for building six soil reflectance composites (SRC) using NDVI, NBR2 and a new index combining the NDVI and a short-wave infrared (SWIR) band (PV+IR2). A comprehensive analysis of the spectral and spatial performance and accuracy of the resulting SRCs proves the flexibility and validity of HISET. Disturbance effects such as spectral confusion of bare soils with non-photosynthetic-active vegetation (NPV) could be reduced by choosing grassland and crops as input LC for HISET. The NBR2-based SRC spectra showed the highest similarity with LUCAS spectra, the broadest spatial coverage of bare soil pixels and the least number of valid observations per pixel. The spatial coverage of bare soil pixels is validated against the database of the Integrated Administration and Control System (IACS) of the European Commission. Validation results show that PV+IR2-based SRCs outperform the other two indices, especially in spectrally mixed areas of bare soil, photosynthetic-active vegetation and NPV. The NDVI-based SRCs showed the lowest confidence values (95%) in all bands. In the future, HISET shall be tested in other areas with different environmental conditions and LC characteristics to evaluate if the findings of this study are also valid.

A digital surface model (DSM) provides the geometry and structure of an urban environment with buildings being the most prominent objects in it. Built-up areas change with time due to the rapid expansion of cities. New buildings are being built, existing ones are expanded, and old buildings are torn down. As a result, 3D surface models can increase the understanding and explanation of complex urban scenarios. They are very useful in numerous fields of remote sensing applications, in tasks related to 3D reconstruction and city modeling, planning, visualization, disaster management, navigation, and decision-making, among others. DSMs are typically derived from various acquisition techniques, like photogrammetry, laser scanning, or synthetic aperture radar (SAR). The generation of DSMs from very high resolution optical stereo satellite imagery leads to high resolution DSMs which often suffer from mismatches, missing values, or blunders, resulting in coarse building shape representation. To overcome these problems, we propose a method for 3D surface model generation with refined building shapes to level of detail (LoD) 2 from stereo half-meter resolution satellite DSMs using deep learning techniques. Mainly, we train a conditional generative adversarial network (cGAN) with an objective function based on least square residuals to generate an accurate LoD2-like DSM with enhanced 3D object shapes directly from the noisy stereo DSM input. In addition, to achieve close to LoD2 shapes of buildings, we introduce a new approach to generate an artificial DSM with accurate and realistic building geometries from city geography markup language (CityGML) data, on which we later perform a training of the proposed cGAN architecture. The experimental results demonstrate the strong potential to create large-scale remote sensing elevation models where the buildings exhibit better-quality shapes and roof forms than just using the matching process. Moreover, the developed model is successfully applied to a different city that is unseen during the training to show its generalization capacity.

The digital transformation taking place in all areas of life has led to a massive increase in digital data – in particular, related to the places where and the ways how we live. To facilitate an exploration of the new opportunities arising from this development the Urban Thematic Exploitation Platform (U-TEP) has been set-up. This enabling instrument represents a virtual environment that combines open access to multi-source data repositories with dedicated data processing, analysis and visualisation functionalities. Moreover, it includes mechanisms for the development and sharing of technology and knowledge. After an introduction of the underlying methodical concept, this paper introduces four selected use cases that were carried out on the basis of U-TEP: two technology-driven applications implemented by users from the remote sensing and software engineering community (generation of cloud-free mosaics, processing of drone data) and two examples related to concrete use scenarios defined by planners and decision makers (data analytics related to global urbanization, monitoring of regional land-use dynamics). The experiences from U-TEP’s pre-operations phase show that the system can effectively support the derivation of new data, facts and empirical evidence that helps scientists and decision-makers to implement improved strategies for sustainable urban development.

Skybox Imaging launched the SkySat 1 and 2 satellites in 2013 and 2014. They are small and low-cost satellites, capable of recording still images with sub-metre resolution and high definition video for up to 90 seconds of a single target, using a novel focal plane with three 5.5 megapixel frame sensors. To improve resolution and signal-to-noise ratio of the still imagery, multiple frames are fused with super-resolution image merging. This article evaluates the SkySat image quality and georeferencing performance. For comparison, Worldview-3 (WV-3) data acquired over the same area is evaluated using the same procedure and reference data. Results show that georeferencing of SkySat still imagery products requires more ground control than other very high resolution sensors. Results from the Las Vegas video show that speed of moving vehicles in videos can be detected to better than 0.8 mph and that automatic motion detection can be used to georeference videos to street vector databases. Generation of digital surface models from video show a height accuracy of 1.2 m (NMAD).

The 3D information of road infrastructures is growing in importance with the development of autonomous driving. In this context, the exact 2D position of road markings as well as height information play an important role in, e.g., lane-accurate self-localization of autonomous vehicles. In this paper, the overall task is divided into an automatic segmentation followed by a refined 3D reconstruction. For the segmentation task, we applied a wavelet-enhanced fully convolutional network on multiview high-resolution aerial imagery. Based on the resulting 2D segments in the original images, we propose a successive workflow for the 3D reconstruction of road markings based on a least-squares line-fitting in multiview imagery. The 3D reconstruction exploits the line character of road markings with the aim to optimize the best 3D line location by minimizing the distance from its back projection to the detected 2D line in all the covering images. Results showed an improved IoU of the automatic road marking segmentation by exploiting the multiview character of the aerial images and a more accurate 3D reconstruction of the road surface compared to the semiglobal matching (SGM) algorithm. Further, the approach avoids the matching problem in non-textured image parts and is not limited to lines of finite length. In this paper, the approach is presented and validated on several aerial image data sets covering different scenarios like motorways and urban regions.

Studies in the last years have proved the outstanding performance of deep learning for computer vision tasks in the remote sensing field, such as disparity estimation. However, available datasets mostly focus on close-range applications like autonomous driving or robot manipulation. To reduce the domain gap while training we present SyntCities, a synthetic dataset resembling the aerial imagery on urban areas. The pipeline used to render the images is based on 3D modelling, which helps to avoid acquisition costs, provides sub-pixel accurate dense ground truth and simulates different illumination conditions. The dataset additionally provides multi-class semantic maps and can be used converted to point cloud format to benefit a wider research community. We focus on the task of disparity estimation and evaluate the performance of the traditional Semi-Global Matching and state of the art architectures, trained with SyntCities and other datasets, on real aerial and satellite images. A comparison with the widely used SceneFlow dataset is also presented. Strategies using a mixture of both real and synthetic samples are studied as well. Results show significant improvements in terms of accuracy for the disparity maps. SyntCities can be downloaded at: https://tinyurl.com/77e3n6m9