Active research projects
In this project, we investigate machine learning algorithms for the purpose of real-time 3D human pose estimation in a hospital monitoring scenario. Patients are typically covered with a blanket and the bed is cluttered with books, laptops and other everyday objects. This makes the task more challenging than background-free human pose estimation. With the constraint of day and night monitoring capacity, we have recently published a method based on depth data which will be presented at MICCAI 2016, see link to the paper below. On this project page, you can also find the used dataset and training code. For further information, please contact Felix Achilles.
Feel free to contact me to any of the following projects or if you have your own project/thesis ideas. Sometimes I have proposals not yet added to the list below.
I am currently involved in conducting research in the following research areas.
- Temporal alignment
- Activity recognition and segmentation
- Human pose estimation.
- Recurrent neural networks.
- 2016 - Master in Artificial Intelligence / Universitat Politècnica de Catalunya (UPC), Barcelona, Spain
- 2011 - Mathematics Engineering / Istanbul Technical University (ITU), Istanbul, Turkey
List of Publications
||J. Postel, F. Ferroni, H. Coskun, N. Navab, F. Tombari
Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation
International Conference on Computer Vision (ICCV), Seoul, Korea, October 2019 [oral].
||H. Coskun, F. Achilles, R. DiPietro, N. Navab, F. Tombari
Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization
International Conference on Computer Vision (ICCV), Venice, Italy, October 2017
||F. Achilles, A.E. Ichim, H. Coskun, F. Tombari, S. Noachtar, N. Navab
PatientMocap: Human Pose Estimation under Blanket Occlusion for Hospital Monitoring Applications
Proceedings of the 19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Athens, Greece, October 2016