Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Computer Vision and Pressure Dynamics in a Chronic Sheep Trial
We are conducting chronic sheep studies to acquire quantitative data on how posture relates to dynamic changes in physiologic pressures. A transfer-learning based computer vision algorithm has been written to estimate posture, extrapolate angles, and synchronize this postural data to simultaneously acquired pressure data but we want to improve robustness and flexibility of the surveillance.
Keywords: Machine Learning
Computer Vision
Signal Processing
Mechanical and Process Engineering
Physiology
Electrical Engineering
With the end goal of the design of an actively controlled "SmartShunt", the hydrocephalus project aims to further illuminate how the cerebrospinal space not only interacts with different branches, but also the bidirectional interactions with other physiologic components of the body. We are conducting chronic sheep studies to acquire quantitative data on how posture relates to dynamic changes in physiologic pressures. A transfer-learning based computer vision algorithm has been written to estimate posture, extrapolate angles, and synchronize this postural data to simultaneously acquired pressure data but we want to improve robustness and flexibility of the surveillance.
With the end goal of the design of an actively controlled "SmartShunt", the hydrocephalus project aims to further illuminate how the cerebrospinal space not only interacts with different branches, but also the bidirectional interactions with other physiologic components of the body. We are conducting chronic sheep studies to acquire quantitative data on how posture relates to dynamic changes in physiologic pressures. A transfer-learning based computer vision algorithm has been written to estimate posture, extrapolate angles, and synchronize this postural data to simultaneously acquired pressure data but we want to improve robustness and flexibility of the surveillance.
1. Create a computer vision algorithm that is able to passively and automatically estimate the posture of sheep using synchronized frames acquire with a dual-camera setup.
2. Use the data acquired from the algorithm to analyze the data to be able to make statements regarding the pose/pressure relationship in our subjects.
1. Create a computer vision algorithm that is able to passively and automatically estimate the posture of sheep using synchronized frames acquire with a dual-camera setup.
2. Use the data acquired from the algorithm to analyze the data to be able to make statements regarding the pose/pressure relationship in our subjects.
1. Knowledge of computer vision methodology 2. Proficient in Python and the command line environment 3. Self-motivated and ability to work in a very interdisciplinary team setting 4. Comfortable working within an in-vivo animal trial setting
The chair of Product Development and Engineering Design at ETH Zurich considers itself a center for system-oriented product development and innovation. Our aspiration consists on the one hand of the advancement and investigation of methods and processes of product development and on the other hand of the development of new technical systems. The purpose of our daily work is to contribute to the innovative ability and competitiveness of Switzerland.
The chair of Product Development and Engineering Design at ETH Zurich considers itself a center for system-oriented product development and innovation. Our aspiration consists on the one hand of the advancement and investigation of methods and processes of product development and on the other hand of the development of new technical systems. The purpose of our daily work is to contribute to the innovative ability and competitiveness of Switzerland.
1. Work in a interdiscpinary team of clinicians and engineers on a large-scale project with wide-reaching implications. 2. Learn about how large, multi-institutional projects operate efficienty. 3. Be a part of a truly novel project
Anthony Podgorsak - ETH Zürich
apodgorsak@ethz.ch
Nina Trimmel - USZ
Nina.Trimmel@usz.ch