Profile
|
M.Sc. Stephanie Käs |
My current research centers on Human Pose Estimation (HPE) as well as gesture and action recognition. Together with my team, I recently completed a project that focused specifically on leveraging fisheye imagery to enhance recognition accuracy.
In my previous work, I contributed to data science projects within the realm of particle physics, specifically the Belle II experiment, and I also engaged in a predictive maintenance use case for railway engineering. Alongside my research, I have gained significant teaching experience and place strong emphasis on clear science communication, as well as agile project and group management.
Current Students
HiWis:
- T. Hilgers
Thesis:
- E. Schönherr (Generative AI)
- L. Markert (Gesture recognition)
Supervision Experience (Former Students)
Master's Thesis (RWTH Aachen):
- V. Hilla: "An Analysis of Error Sources to Improve Temporal Consistency in 3D Human Pose Estimation" (July 2024)
- A. Burenko: "Stabilization, Tracking, and Gesture Recognition Methods within Skeleton-based Human Pose Estimation Framework" (September 2024)
- H. Thillmann: "Re-Engineering an Absolute Pose Estimation Architecture: Enabling Extensibility via Modularization" (October 2024)
Bachelor's Thesis:
- T. Schellhaas (JLU Gießen)
Project Leader:
- Stratospheric Balloon Research Project: "StratoGI" (JLU Gießen)
Others: - S. Peter (research collaboration) - several HiWis
Teaching & Speaker Experience
Public Speaker:
- Student Hybrid Rocket Team: "HybridLaunch"
Guest Speaker:
- HASCO Summer School
- ErUM-Data-Hub
Teaching Assistant:
- Machine Learning and Computer Vision (RWTH Aachen)
- Proseminar Historical Milestones of Machine Learning (RWTH Aachen)
- Seminar Current Milestones in Machine Learning and Computer Vision (RWTH Aachen)
- Physics Basic Lab Course (JLU Gießen)
Lecturer:
- Statistics for Geosciences (2021–2023, JLU Gießen)
