The abstract should appear at the top of the left-hand column of text, about 0.5 inch (12 mm) below the title area and no more than 3.125 inches (80 mm) in length. Leave a 0.5 inch (12 mm) space between the end of the abstract and the beginning of the main text. The abstract should contain about 100 to 150 words, and should be identical to the abstract text submitted electronically along with the paper cover sheet. All manuscripts must be in English, printed in black ink.

Soils contain the largest global carbon pool and thus, play an important role in atmospheric CO2 sequestration through increase in soil organic carbon (SOC) stock (Minasny et al., 2017). Therefore, large scale mapping and reporting of soil status, quality and health is starting to get a requirement amongst policy-makers and implemented in target setting of the Sustainable Development Goals and relevant EU policies. Soil quality and health monitoring is commonly described as a sum of physical, chemical and biological properties of soils. Since many years, multispectral and hyperspectral Earth Observation (EO) have been valuable data sources for analyzing the chemical and physical constitution of top soils (Chabrillat et al., 2019). Mainly two approaches are used, the Digital Soil Modelling (DSM) approach as well as the Spectral Soil Modelling (SSM) approach. Both approaches assimilate EO data products such as information regarding the vegetation dynamics and exposed soil reflectance data.

Soil organic matter is essential for preserving and maintaining a range of soil and ecosystem functions as well as supply and store carbon for climate change mitigation. Digital Soil Mapping techniques will be used to obtain a spatially continuous product, especially over permanently vegetated areas. Recently available satellite remote sensing data, with among other systems the Copernicus Sentinel, will be used as input for environmental covariates. Digital Soil Mapping, coupled together with Remote Sensing products, is a powerful tool to produce soil properties maps and monitoring the changes in soil conditions over time.

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.

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.

In this paper, we propose an algorithm for robustly fusing digital surface models (DSMs) with different ground sampling distances and confidences, using explicit surface priors to obtain locally smooth surface models. Robust fusion of the DSMs is achieved by minimizing the L1-distance of each pixel of the solution to each input DSM. This approach is similar to a pixel-wise median, and most outliers are discarded. We further incorporate local planarity assumption as an additional constraint to the optimization problem, thus reducing the noise compared with pixel-wise approaches. The optimization is also inherently able to include weights for the input data, therefore allowing to easily integrate invalid areas, fuse multiresolution DSMs, and to weight the input data. The complete optimization problem is constructed as a variational optimization problem with a convex energy functional, such that the solution is guaranteed to converge toward the global energy minimum. An efficient solver is presented to solve the optimization in reasonable time, e.g., running in real time on standard computer vision camera images. The accuracy of the algorithms and the quality of the resulting fused surface models are evaluated using synthetic data sets and spaceborne data sets from different optical satellite sensors.

Digital surface models can be efficiently generated with automatic image matching from optical stereo images. Modern satellites, such as WorldView-1 and 2 can acquire multiple views of an area in the same orbit. These datasets offer high redundancy and thus allow higher quality 3D reconstructions than previously possible. This paper evaluates multiple DSM generation algorithms based on dense image matching on a 25 view dataset acquired by the WorldView-2 satellite. Fusion of the images is performed at different stages of image matching and results are compared to reveal the advantages and disadvantages of each method.

Mobile phones are now ubiquitous and many of these now include micro-browsers. We explore the potential, and the limitations, of widely available WAP technology for online control and monitoring of a robot. A mobile phone interface for a 4 joint hydraulic manipulator has been developed and was successfully tested.