I received an MSc degree (Dipl.-Ing.) and a PhD degree (Dr.techn.) in Telematics from Graz University of Technology in 2009 and 2014, respectively. Currently, I am a postdoctoral researcher at the Institute of Computer Graphics and Vision in the group of Professor Vincent Lepetit.
During my PhD studies, my research was focused on inter-camera person re-identification via (on-line) machine learning considering different feature representations and metric spaces. Additionally, I was involved in the Person ReID (ECV), the OUTLIER, the KiwiVision Cloud and the Mobi-Trick project.
I was also working on augmented reality (AR) technologies for CultAR, an EU FP7 project targeted at enhancing tourists’ experience when exploring cultural contents in urban environments. In particular, I was responsible for providing accurate estimates of the 6 degrees of freedom (DoF) camera pose of mobile devices such as smartphones or tablets to the overall system. In order to ensure real-time behavior despite the typically limited computational power of mobile platforms, this was realized by running a lightweight, relative rotation tracker (3 DoF) on top of an absolute, full 6 DoF localization service.
More recently, I worked on 3D camera tracking in urban environments based on 2.5D city maps and a semantic segmentation of the input frames. Specifically, by exploiting semantic image information, we were able to compensate for typical tracking inaccuracies such as drift.
Currently, my research is focused on indoor environments, in particular on the estimation of a room’s layout from a single RGB image. The goal is to find the boundaries between the floor, individual walls and the ceiling, which allows to infer the spatial layout. While this is very beneficial for many applications such as AR, indoor navigation, scene reconstruction and object detection, it is inherently challenging due to potentially severe occlusions, clutter, difficult lighting and large intra-class variance.