Register now After registration you will be able to apply for this opportunity online.
Real-Time Hand Contact Detection from Sparse Views for Infection Prevention in Surgery
This thesis focuses on developing a real-time capable system to detect hand contacts of medical staff during surgical procedures. The proposed system will be used to detect potential breaches in hand hygiene protocols and warn medical staff before contact with the patient.
Keywords: Healthcare, Computer Vision, Deep Learning, Machine Learning, Hand Contact Detection
This thesis is done in collaboration with the USZ and is centered around a dataset of over 20 real anesthesia inductions collected from 6 RGB-D cameras. The goal will be to create a light-weight and real-time capable hand contact detection system from sparse views (only 1-2 camera views). The proposed system will be used to detect potential breaches in hand hygiene protocols and warn medical staff before contact with the patient. The dataset is already annotated with the ground-truth 3D human body poses and meshes of the medical staff and the relevant objects and key areas in the room.
This thesis is done in collaboration with the USZ and is centered around a dataset of over 20 real anesthesia inductions collected from 6 RGB-D cameras. The goal will be to create a light-weight and real-time capable hand contact detection system from sparse views (only 1-2 camera views). The proposed system will be used to detect potential breaches in hand hygiene protocols and warn medical staff before contact with the patient. The dataset is already annotated with the ground-truth 3D human body poses and meshes of the medical staff and the relevant objects and key areas in the room.
You will be introduced to the dataset and our key project partners. Your tasks include:
- Literature research for appropriate methods for real-time hand contact detection
- Implementation and training of the proposed detection system
- Exploring feedback mechanisms to the medical staff
You will be introduced to the dataset and our key project partners. Your tasks include:
- Literature research for appropriate methods for real-time hand contact detection
- Implementation and training of the proposed detection system
- Exploring feedback mechanisms to the medical staff
- Strong programming skills (Python, C#, C++, …) - Experience with machine learning, data science or computer vision (Pytorch, OpenCV, …) - The ability to take initiative and shape the direction of the project - Enthusiasm for tackling practical challenges
Not specified
- Collaboration with USZ - Master thesis / Semester Project - CV / ML
Please send your CV and masters grades to Sophokles Ktistakis (ktistaks@ethz.ch)
Please send your CV and masters grades to Sophokles Ktistakis (ktistaks@ethz.ch)
