Register now After registration you will be able to apply for this opportunity online.
3D Semantic Segmentation during Anesthesia Induction
The goal of this thesis is to create a system for 3D semantic segmentation of anesthesia procedures from multiple RGB-D cameras. We are looking for a motivated student who is passionate about applying machine learning and computer vision methods and working with a multi-camera setup in a surgical setting.
Keywords: Computer Vision, Machine Learning, Body Reconstruction, Semantic Segmentation
This project focuses on analyzing the transmission of bacteria during anesthesia induction procedures, where multiple medical professionals work closely with the patient. The goal of the thesis is to map potential bacterial transmission pathways by integrating 3D segmentation of the surgical room with body pose reconstruction of the medical team, emphasizing their hand-to-surface interactions. The thesis aims to create and implement algorithms for semantic scene understanding and body pose reconstruction. They will be applied to a dataset of actual anesthesia inductions recorded at the USZ, providing valuable insights into the spread of bacteria in medical settings.
This project focuses on analyzing the transmission of bacteria during anesthesia induction procedures, where multiple medical professionals work closely with the patient. The goal of the thesis is to map potential bacterial transmission pathways by integrating 3D segmentation of the surgical room with body pose reconstruction of the medical team, emphasizing their hand-to-surface interactions. The thesis aims to create and implement algorithms for semantic scene understanding and body pose reconstruction. They will be applied to a dataset of actual anesthesia inductions recorded at the USZ, providing valuable insights into the spread of bacteria in medical settings.
Literature Review: Semantic Segmentation and Body Pose Reconstruction
Point cloud fusion from multiple cameras
Implementing segmentation and body pose reconstruction methods on the dataset
Literature Review: Semantic Segmentation and Body Pose Reconstruction
Point cloud fusion from multiple cameras
Implementing segmentation and body pose reconstruction methods on the dataset
- Good programming skills in Python (or Java, C#, C, C++) - Experience with machine (deep) learning and computer vision - Previous hands-on experience with frameworks such as PyTorch, OpenCV, scikit-learn - Methodical way of working - Ability to take ownership in shaping the direction of the project
As part of our research at the AR Lab within the Human Behavior Group we are working on automatically analyzing a user’s interaction with his environment in scenarios such as surgery or in industrial machine interactions. By collecting real-world datasets during those scenarios and using them for machine learning tasks such as activity recognition, object pose estimation or image segmentation we can gain an understanding of how a user performed during a given task. We can then utilize this information to provide the user with real-time feedback on his task using mixed reality devices, such as the Microsoft HoloLens, that can guide him and prevent him from doing mistakes.
As part of our research at the AR Lab within the Human Behavior Group we are working on automatically analyzing a user’s interaction with his environment in scenarios such as surgery or in industrial machine interactions. By collecting real-world datasets during those scenarios and using them for machine learning tasks such as activity recognition, object pose estimation or image segmentation we can gain an understanding of how a user performed during a given task. We can then utilize this information to provide the user with real-time feedback on his task using mixed reality devices, such as the Microsoft HoloLens, that can guide him and prevent him from doing mistakes.
- Master Thesis / Semester Thesis - ML / CV - 3D Semantic Segmentation - USZ Collaboration
Please send your CV and master course grades to Sophokles Ktistakis (ktistaks@ethz.ch)
Please send your CV and master course grades to Sophokles Ktistakis (ktistaks@ethz.ch)