Organisation: TU Munich
Address: Boltzmannstrasse 3, 85748 Garching, Germany
Contact: Prof. Dr. Daniel Cremers (Tel: +49-89-289-17755, flyers(at)vision.in.tum.de)
- Jakob Engel (TUM)
- Christian Kerl (TUM)
- Jörg Stückler (TUM)
- Vladyslav Usenko (TUM)
Our team is part of the Computer Vision Group at the TUM. The group investigates topics such as 3D reconstruction, 3D simultaneous localization and mapping (SLAM), optical flow estimation, and visual odometry with monocular, stereo, and RGB-D cameras, which it also develops for the autonomous navigation of micro aerial vehicles (MAVs). For instance, the group participates in the DFG Research Unit FOR 1505 “Mapping on Demand” which tackles autonomous semantic mapping using MAVs.
The team consists of three researchers (one PostDoc and two PhD students) and has a strong background in scientific research and hands-on experience in developing autonomous quadrocopters. Jakob Engel is a PhD student in the Computer Vision Group. He received his Master’s degree for his thesis on “Autonomous Camera-Based Navigation of a Quadrocopter” for which he has been awarded with the Siemens Award for the best Master’s thesis in 2012. His current research interests include semi-dense visual odometry and SLAM with monocular cameras which is of high relevance to the challenge objectives. Christian Kerl also is a PhD student in the Computer Vision Group. In his Master’s thesis, he developed visual odometry with RGB-D cameras for autonomous MAVs. Currently, he pursues dense visual 3D surface reconstruction and SLAM with RGB-D cameras. His work on Dense Visual Odometry (DVO) was nominated for the ICRA 2013 Best Vision Paper.
- Scale-Aware Navigation of a Low-Cost Quadrocopter with a Monocular Camera (J. Engel, J. Sturm, D. Cremers), In Robotics and Autonomous Systems (RAS), 2014.
- Dense Tracking and Mapping with a Quadrocopter (J. Sturm, E. Bylow, F. Kahl, D. Cremers), In Unmanned Aerial Vehicle in Geomatics (UAV-g), 2013.
- Robust Odometry Estimation for RGB-D Cameras (C. Kerl, J. Sturm, D. Cremers), In Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), 2013
- LSD-SLAM: Large-Scale Direct Monocular SLAM (J. Engel, T. Schöps, D. Cremers), In European Conference on Computer Vision (ECCV), 2014.
- Large-Scale Multi-Resolution Surface Reconstruction from RGB-D Sequences (F. Steinbruecker, C. Kerl, J. Sturm, D. Cremers), In IEEE International Conference on Computer Vision (ICCV), 2013.