Search

Building semantic segmentation is a crucial task for building information modeling (BIM). Current research generally exploits terrestrial image data, which provides only limited view of a building. By contrast, oblique imagery acquired by unmanned aerial vehicle (UAV) can provide richer information of both the building and its surroundings at a larger scale. In this paper, we present a novel pipeline for building semantic segmentation from oblique UAV images using a fully convolutional neural network (FCN). To cope with the lack of UAV image annotations at facade level, we leverage existing ground-view facades databases to simulate various aerial-view images based on estimated homography, yielding abundant synthetic aerial image annotations as training data. The FCN is trained end-to-end and tested on full-tile UAV images. Experiments demonstrate that the incorporation of simulated views can significantly boost the prediction accuracy of the network on UAV images and achieve reasonable segmentation performance.

In this paper we present our work on enabling Balloon launched high altitude UAV Missions for an autopilot system previously used only at lower levels in visual line of sight conditions. One field of our research in the context of flying robotics is focused on high altitude pseudo satellites (HAPS). To gain operational experience in high altitude flying and for system and payload testing, a balloon launched small UAV (sub 10kg) system was designed including building an optimized airframe. Balloon launching was chosen because it offers fast and clearly regulated access to the desired altitudes. Our autopilot system has proven its capabilities in many years of flight experiments with different platforms (helicopter and fixed wing). The main characteristics are modularity and easy use for scientists. On the hardware level the task was to integrate the existing segmented systems of the research autopilot in a compact form factor, with the possible use in larger platforms in mind. The design was driven by the special thermal requirements resulting from flying in stratospheric conditions. In the autopilot software, several mission specific functions had to be added, which only required moderate effort due to the modular system design. Major changes included adding a flight termination manager. A launch routine was developed allowing a safe transition from free-fall to stable horizontal flight in thin air after being dropped from the balloon. Extensive testing was performed to validate the design. Simulating the mission, including balloon ascend, was used to check the mission software. Thermal and pressure conditions at altitude were replicated in a thermal vacuum chamber with additional sensors applied to identify problems. The simulation and control laws were verified by means of low altitude test flights.

Very high resolution satellite imagery used to be a rare commodity, with infrequent satellite pass-over times over a specific area-of-interest obviating many useful applications. Today, more and more such satellite systems are available, with visual analysis and interpretation of imagery still important to derive relevant features and changes from satellite data. In order to allow efficient, robust and routine image analysis for humanitarian purposes, semi-automated feature extraction is of increasing importance for operational emergency mapping tasks. In the frame of the European Earth Observation program COPERNICUS and related research activities under the European Union's Seventh Framework Program, substantial scientific developments and mapping services are dedicated to satellite based humanitarian mapping and monitoring. In this paper, recent results in methodological research and development of routine services in satellite mapping for humanitarian situational awareness are reviewed and discussed. Ethical aspects of sensitivity and security of humanitarian mapping are deliberated. Furthermore methods for monitoring and analysis of refugee/internally displaced persons camps in humanitarian settings are assessed. Advantages and limitations of object-based image analysis, sample supervised segmentation and feature extraction are presented and discussed.