Dr. Bertram Taetz
E-Mail: | bertram.taetz@dfki.de |
---|---|
Position: | Senior Researcher |
Bertram Taetz joined the Department Augmented Vision of the German Research Center for Artificial Intelligence (DFKI GmbH) in Kaiserslautern as Senior Researcher in April 2013. He studied Mathematics and Physics in Germany and England (Durham University) and received his M.Sc. from Ruhr University Bochum (RUB), Germany, in 2009. Focusing on numerical methods for dynamical systems, he received his PhD in Mathematics from Ruhr University Bochum in 2012. He was deputy group leader of the wearHEALTH group at the Technische Universität Kaiserslautern, from 2015 to 2019, and is currently a group leading Senior Researcher at DFKI. He is working on methods to combine probabilistic sensor fusion with scalable statistical machine learning methods. Applications are (inertial) human motion tracking, analysis and simulation as well as motion estimation from videos (optical flow), marker less human motion tracking, human surface registration and other rigid and non-rigid image as well as point cloud registrations with 2D and 3D data. An extensive list of publications can also be found on ResearchGate.
JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 1; peer review: awaiting peer review]
In: Open Research Europe, Vol. 4, No. 33, Pages 0-0, Open Research Europe, 2024.
Details
| Link 1
On motion artifacts arising when integrating inertial sensors into loose clothing such as a working jacket
In: Proceedings of the 9th International Conference on Control, Decision and Information Technologies. International Conference on Control, Decision and Information Technologies (CoDIT-2023), July 3-6, Rom, Italy, IEEE Xplore, 2023.
Details
| Link 1
DIVENET: Dive Action Localization and Physical Parameter Extraction for High Performance Training
In: IEEE Access (IEEE), Vol. IEEE Access, No. 11, Pages 37749-37767, IEEE, 4/2023.
Details
| Link 1
| Link 2
Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes
Proceedings of IEEE International Conference on Pattern Recognition (ICPR). International Conference on Pattern Recognition (ICPR-2022) IEEE 2022 .
Details
| Link 1
Towards Inertial Human Motion Tracking with Drift-Free Absolute Orientations using only Sparse Sources of Heading Information
Proceedings of the 25th International Conference on Information Fusion in Linköping. International Conference on Information Fusion (FUSION-2022) July 4-7 Linköping Sweden IEEE Explore 2022 .
Details
| Link 1
Towards Artefact Aware Human Motion Capture using Inertial Sensors Integrated into Loose Clothing
Proceedings of 2022 IEEE International Conference on Robotics and Automation 2022. IEEE International Conference on Robotics and Automation (ICRA-2022) May 23-27 Philadelphia PA United States IEEE 5/2022 .
Details
Latenzarme Erkennung vonWassersprungbewegungen in Trainingsvideos
In: 20. Frühjahrsschule "Technologien im Leistungssport". Frühjahrsschule "Technologien im Leistungssport", September 7-8, Leipzig, Germany, IAT, Leipzig, 9/2022.
Details
Magnetometer Robust Deep Human Pose Regression With Uncertainty Prediction Using Sparse Body Worn Magnetic Inertial Measurement Units
IEEE Access (IEEE) 9 Seiten 36657-36673 IEEE 2/2021 .
Details
| Link 1
| Link 2
Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function
Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE Winter Conference on Applications of Computer Vision (WACV-2021) January 5-9 Online IEEE 2021 .
Details
| Link 1
| Link 2
Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, 2018.
Details
| Link 1
| Link 2
Optical Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
In: ArXiv e-prints, Vol. 1703.02563, arXiv.org, 3/2017.
Details
A Framework for an Accurate Point Cloud Based Registration of Full 3D Human Body Scans
IAPR Conference on Machine Vision Applications (MVA-17), March 8-12, Nagoya, Japan
Details
| Link 1
A Probablistic Combination of CNN and RNN Estimates for Hand Gesture Based Interaction in Car
16th IEEE International Symposium on Mixed and Augmented Reality (ISMAR) IEEE International Symposium on Mixed and Augmented Reality (ISMAR-17), October 9-13, Nantes, France
Details
| Link 1
Optical Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
Details
Occlusion-Aware Video Registration for Highly Non-Rigid Objects
IEEE Winter Conference on Applications of Computer Vision (WACV-2016), March 7-9, Lake Placid, NY, USA
Details
| Link 1
Extended Coherent Point Drift Algorithm with Correspondence Priors and Optimal Subsampling
IEEE Winter Conference on Applications of Computer Vision (WACV-2016), March 7-9, Lake Placid, NY, USA
Details
| Link 1
| Link 2
Adding Model Constraints to CNN for Top View Hand Pose Recognition in Range Images
Proceedings of the 5th International Conference in Pattern Recognition Applications and Methods ICPRAM 2016 International Conference on Pattern Recognition Applications and Methods (ICPRAM-05), 5th, February 24-26, Rome, Italy
Details
| Link 1
Joint Pre-Alignment and Robust Rigid Point Set Registration
IEEE International Conference on Image Processing (ICIP-16), September 25-29, Phoenix, AZ, USA
Details
| Link 1
Two Phase Classification for Early Hand Gesture Recognition in 3D Top View Data
International Symposium on Visual Computing : Advances in Visual Computing International Conference on Visual Computing (ISVC-16), Advances in Visual Computing, December 12-14, Las Vegas, Nevada, USA
Details
Occlusion-Aware Video Registration for Highly Non-Rigid Objects Supplementary Material
Details
| Link 1
Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
Proceedings - 2015 IEEE International Conference on Computer Vision International Conference on Computer Vision (ICCV-15), December 13-16, Santiago, Chile
Details
| Link 1
| Link 2
| Link 3
| Link 4
Using Mutual Independence of Slow Features for Improved Information Extraction and Better Hand-Pose Classification
Details
| Link 1
Ambulatory inertial spinal tracking using constraints
Proceedings of the 9th International Conference on Body Area Networks International Conference on Body Area Networks (Bodynets-09), October 29 - November 1, London, United Kingdom
Details