Here we present the operational, fully automatic processing system CATENA developed at DLR. The uniform pre-processing of an increasing amount of satellite data for generation of whole coverages of e.g. Europe for one time or of time-series for one location covering many years is requested more and more. Such requirements contain the processing of huge amounts of data which can hardly be handled manually. So a fully automatic pre-processing environment was developed at the Remote Sensing Technology Institute of DLR in Oberpfaffenhofen since 2006. This processing environment named CATENA was designed for uniform, automatic general purpose processing of huge amounts of optical satellite data of similar type. In this paper we present the concept of the processing system, the framework and the decomposition of processing requirements to processing modules and processing chains. We give some examples for already implemented general purpose or project specific processing chains and an analysis of performance and quality of the results.
The upraise of autonomous driving technologies asks for maps characterized bya broad range of features and quality parameters, in contrast to traditional navigation maps which in most cases are enriched graph-based models. This paper tackles several uncertainties within the domain of HD Maps. The authors give an overview about the current state in extracting road features from aerial imagery for creating HD maps, before shifting the focus of the paper towards remote sensing technology. Possible data sources and their relevant parameters are listed. A random forest classifier is used, showing how these data can deliver HD Maps on a country-scale, meeting specific quality parameters.
5 December 2023 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Remotely sensed Earth elevation data or digital surface model (DSM) typically contains both terrain and above-ground information such as vegetation and man-made constructions. However, many applications require pure bare-terrain data, also known as digital terrain model (DTM). But how do we separate 3D objects on the DSM from the ground? The most commonly used approaches are still based on various filtering techniques, which in turn involve the pre-definition of thresholds or specific parameters depending on the inhomogeneity of the scene. Despite many long existing and newly developed approaches the general fully automatic extraction of large-scale, reliable DTMs is still a problem – especially the preservation of steep terrain features in terraced landscapes. In this context, we explore several deep learning models and select one based on the EfficientNet architecture. This model serves as an encoder in the UNet-shaped framework and – despite its relatively low amount of parameters compared to common network architectures – it can automatically distinguish non-ground pixels and estimate the bare-ground height information while maintaining the complexity of the anthropogenic geomorphology of landscapes. In a series of experiments, we demonstrate that the DTM generated with the proposed method significantly outperforms other DTM generation approaches – both quantitatively and qualitatively. To enable further comparisons with our methodology the training, validation and test datasets have been collected together and made available at https://github.com/KseniaBittner/DSM2DTM.
With the availability of very high resolution (VHR) satellite images fast and relatively cheap investigations of large urban areas in comparison to aerial photography are possible. In urban areas a predominant use of satellite data is the generation of city models for applications like mobile phone signal propagation or flooding and catastrophe simulation. Since more and more large and quick growing cities emerge in developing countries, monitoring and modeling of these areas from satellite will be the cheapest if not the only possibility. Most of the actual methods used for the generation of city models depend on mainly manual work. A method for automatic derivation of -in a first step very coarse -models of urban environments will be of great use. In this paper a production chain and the methods used for such a automatic modeling is presented. The method is based on stereo images from VHR satellite stereo imagery provided, e.g., by IKONOS or QuickBird. In a first step a digital surface model (DSM) is derived from the stereo data. Subsequently a digital terrain model (DTM) and ortho images are created. Based on the local height differences between DSM and DTM and the normalized difference vegetation index (NDVI) a coarse classification can be made. Upon this classification object models can be selected and object parameters can be adapted to create an object-based representation of the satellite image scene. The method used is evaluated and the results are discussed.
7 September 2012 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
In this paper a new approach for a more detailed post processing and filling of digital elevation models (DEMs) in urban areas is presented. To reach the required specifications in a first step the errors in digital surface models (DSMs) generated by dense stereo algorithms are analyzed and methods for detection and classification of the different types of errors are implemented. Subsequently the classified erroneous areas are handled in separate manner to eliminate outliers and fill the DSM properly. The errors which can be detected in DSMs range from outliers – single pixels or small areas containing extremely high or low values – over noise from mismatches, single small holes to occlusions, where large areas are not visible in one of the images of the stereo pair. To validate the presented method artificial DSMs are generated and superimposed with all different kinds of described errors like noise (small holes cut in), outliers (small areas moved up/down), occlusions (larger areas beneath steep walls) and so on. The method is subsequently applied to the artificial DSMs and the resulting filled DSMs are compared to the original artificial DSMs without the introduced errors. Also the method is applied to stereo satellite generated DSMs from the ISPRS Comission 1 WG4 benchmark dataset and the results are checked with the also provided first pulse laser DSM data. Finally the results are discussed, strengths and weaknesses of the approach are shown and suggestions for application and optimization are given.
31 May 2017 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Automatic rooftop extraction is one of the most challenging problems in remote sensing image analysis. Classical 2D image processing techniques are expensive due to the high amount of features required to locate buildings. This problem can be avoided when 3D information is available. In this paper, we show how to fuse the spectral and height information of stereo imagery to achieve an efficient and robust rooftop extraction. In the first step, the digital terrain model (DTM) and in turn the normalized digital surface model (nDSM) is generated by using a newly step-edge approach. In the second step, the initial building locations and rooftop boundaries are derived by removing the low-level pixels and high-level pixels with higher probability to be trees and shadows. This boundary is then served as the initial level set function, which is further refined to fit the best possible boundaries through distance regularized level-set curve evolution. During the fitting procedure, the edge-based active contour model is adopted and implemented by using the edges indicators extracted from panchromatic image. The performance of the proposed approach is tested by using the WorldView-2 satellite data captured over Munich.