Jürgen Wohlfeil

Vision based rail track and switch recognition for self-localization of trains in a rail network

A collision avoidance system for railroad vehicles needs to determine their location in the railroad network precisely and reliably. For a vehicle-based system, that is independent from the infrastructure, it is vital to determine the direction a railroad vehicle turns at switches. In this paper a vision based approach is presented that allows to achieve this reliably, even under difficult conditions. In the images of a camera that observes the area in front of a railroad vehicle the rail tracks are detected in real-time. From the perspective of the moving railroad vehicle rail tracks branch and join from/to the currently travelled rail track. By tracking these rail tracks in the images, switches are detected as they are passed. It is shown that the followed track can be determined at branching switches. The approach is tested with real data from test rides in different locations and under a variety of weather conditions and environments. It proved to be very robust and of high practical use for track-selective self-localization of railroad vehicles, mandatory for collision avoidance.

A modular, interactive software-concept for radiometric and geometric correction of airborne and spaceborne linescanner images

To generate ortho photos and terrain models from airborne and spaceborne linescanner images, various complex radiometric and geometric corrections have to be applied to the raw images. In this contribution a software-concept is presented, that allows the configuration and application of a modular and expandable chain of such corrections through an interactive graphical user interface. The effect of any changed correction parameter is visualized immediately in zoomable preview-windows. Different correction-steps are illustrated with respect to the generation of terrain models with Semi-Global Matching (SGM), including radiometric sensor and atmosphere correction, as well as sensor boresightalignment calculation and aerotriangulation.

Airborne camera and spectrometer experiments and data evaluation

New stereo push broom camera systems have been developed at German Aerospace Centre (DLR). The new small multispectral systems (Multi Functional Camerahead - MFC, Advanced Multispectral Scanner - AMS) are light weight, compact and display three or five RGB stereo lines of 8000, 10 000 or 14 000 pixels, which are used for stereo processing and the generation of Digital Surface Models (DSM) and near True Orthoimage Mosaics (TOM). Simultaneous acquisition of different types of MFC-cameras for infrared and RGB data has been successfully tested. All spectral channels record the image data in full resolution, pan-sharpening is not necessary. Analogue to the line scanner data an automatic processing chain for UltraCamD and UltraCamX exists. The different systems have been flown for different types of applications; main fields of interest among others are environmental applications (flooding simulations, monitoring tasks, classification) and 3D-modelling (e.g. city mapping). From the DSM and TOM data Digital Terrain Models (DTM) and 3D city models are derived. Textures for the facades are taken from oblique orthoimages, which are created from the same input data as the TOM and the DOM. The resulting models are characterised by high geometric accuracy and the perfect fit of image data and DSM. The DLR is permanently developing and testing a wide range of sensor types and imaging platforms for terrestrial and space applications. The MFC-sensors have been flown in combination with laser systems and imaging spectrometers and special data fusion products have been developed. These products include hyperspectral orthoimages and 3D hyperspectral data.

Uncertainty Model for Template Feature Matching

Using visual odometry and inertial measurements, indoor and outdoor positioning systems can perform an accurate self-localization in unknown, unstructured environments where absolute positioning systems (e.g. GNSS) are unavailable. However, the achievable accuracy is highly affected by the residuals of calibration, the quality of the noise model, etc. Only if these unavoidable uncertainties of sensors and data processing can be taken into account and be handled via error propagation, which allows to propagate them through the entire system. The central filter (e.g. Kalman filter) of the system can then make use of the enhanced statistical model and use the propagated errors to calculate the optimal result. In this paper, we focus on the uncertaintiy calculation of the elementary part of the optical navigation, the template feature matcher. First of all, we propose a method to model the image noise. Then we use Taylor’s theorem to extend two very popular and efficient template feature matchers sum-of-absolute-differences (SAD) and normalized-cross-correlation (NCC) to get sub-pixel matching results. Based on the proposed noise model and the extended matcher, we propagate the image noise to the uncertainties of sub-pixel matching results. Although the SAD and NCC are used, the image noise model can be easily combined with other feature matchers. We evaluate our method by an Integrated Positioning System (IPS) which is developed by German Aerospace Center. The experimental results show that our method can improve the quality of the measured trajectory. Moreover, it increases the robustness of the system.

IPS – a vision aided navigation system

Abstract Ego localization is an important prerequisite for several scientific, commercial, and statutory tasks. Only by knowing one’s own position, can guidance be provided, inspections be executed, and autonomous vehicles be operated. Localization becomes challenging if satellite-based navigation systems are not available, or data quality is not sufficient. To overcome this problem, a team of the German Aerospace Center (DLR) developed a multi-sensor system based on the human head and its navigation sensors – the eyes and the vestibular system. This system is called integrated positioning system (IPS) and contains a stereo camera and an inertial measurement unit for determining an ego pose in six degrees of freedom in a local coordinate system. IPS is able to operate in real time and can be applied for indoor and outdoor scenarios without any external reference or prior knowledge. In this paper, the system and its key hardware and software components are introduced. The main issues during the development of such complex multi-sensor measurement systems are identified and discussed, and the performance of this technology is demonstrated. The developer team started from scratch and transfers this technology into a commercial product right now. The paper finishes with an outlook.