Short CV

Born in 1982 in Warburg, Germany, I studied computer science at the University of Kassel, Germany. After finishing my Bachelor's thesis which deals with an algorithm for semiautomatic color calibration of a omni-directional camera, I moved 2007 to Graz. Here, I finished in 2010 my master in computer science with focus on computer vision and computational intelligence. The title of my master's thesis is "Large-scale robotic SLAM through visual mapping" and was supervised by Prof. Dr. Horst Bischof. In 2011, I joined the PhD program at the ICG. I'm a member of the aerial vision group and we are developing algorithms for 3D reconstruction acquired by micro aerial vehicles.

Research interests

• Structure from Motion (SfM)
• Autonomous flying vehicles
• Visualization of 3D reconstruction results
• Mobile devices programming
• Robot scoccer

Projects

CONSTRUCT

I'm working in the project CONSTRUCTS whose aim is to reconstruct a construction site using images acquired by an MAV. The reconstruction is performed on a daily basis which allows us to detect semantic meaningful changes over time. More information and results can be found here

Photogrammetric Camera Network Design for Micro Aerial Vehicles

Micro Aerial Vehicles (MAVs) equipped with high resolution cameras have the ability of cost efficient and autonomous image acquisition from unconventional viewpoints. To fully exploit the limited flight-time of current MAVs view planning is essential for complete and precise 3D scene sampling. We propose a novel camera network design algorithm suitable for MAVs for close range photogrammetry that exploits prior knowledge of the surrounding. Our algorithm automatically determines a set of camera positions that guarantees important constraints for image based 3D reconstruction. On synthetic experiments we demonstrate that our camera network design obtains detailed 3D reconstructions with a reduced number of images at the desired accuracy level. Comparable results are also computed on an outdoor experiment using our MAV in autonomous flight mode. The full paper and an video can be found here

Efficient Structure from Motion with Weak Position and Orientation Priors

In this paper we present an approach that leverages prior information from global positioning systems and inertial measurement units to speedup structure from motion computation. We propose a view selection strategy that advances vocabulary tree based coarse matching by also considering the geometric configuration between weakly oriented images. Furthermore, we introduce a fast and scalable reconstruction approach that relies on global rotation registration and robust bundle adjustment. Real world experiments are performed using data acquired by a micro aerial vehicle attached with GPS/INS sensors. Our proposed algorithm achieves orientation results that are sub-pixel accurate and the precision is on a par with results from incremental structure from motion approaches. Moreover, the method is scalable and computationally more efficient than previous approaches.

A. Irschara, C. Hoppe, S. Kluckner, H. Bischof. Workshop of Aerial Video Processing (WAVP) in conjunction with CVPR 2011. (PDF), Video

Master's thesis

Simultaneous Localization and Mapping (SLAM) in a three-dimensional environment is an essential requirement for autonomous mobile robots to accomplish high level tasks. An emerging sensor for SLAM is the digital camera, because it is cheap, small, has low weight and can be applied in many different application areas like marine, aerial or land robotics. Today's camera-based solutions, called visual SLAM, are limited to small environments like desktop or oce scenes because of geometric error propagation and limited scalability. In this master thesis, we developed a SLAM system that allows us to handle large-scale environments using a stereo-camera mounted on a wheeled robot. Our approach extends a keyframe-based method for augmented reality applications by adding appearance-based loop detection and correction. Furthermore, we propose a method for incorperating other sensor information like odometry into the visual SLAM framework. We are hereby able to preserve connectivity between camera poses even if visual features are absent. To maintain map accuracy without sacricing excessive computation time, we combine feature descriptors of different strength for data association. In the experiments, we show that our approach is able to handle trajectories of several hundred meters and containing several thousand visual features. The resulting threedimensional maps have correct metric scale. The absolute trajectory error is below one percent. On a standardized benchmark dataset providing groundtruth trajectories, our system outperforms other visual SLAM algorithms by a factor of two. The video shows the mapping result of my thesis of an image sequence acquired in a typical indoor environment. The thesis can be found here