The motivation of this project is to provide a mobile solution that will be able to extract 3D information from athletes on the field without the use of the previous setup. The goal of the project is to extract similar information with the use of a device as portable as a cellphone.
Our group has used multiple different packages available on GitHub that use deep learning techniques to produce estimates of 3D poses using 2D key points. We have successfully produced predicted 3D poses using both trained datasets and custom footage provided by the exercise science group. The most successful package we have used has been VideoPose3D. Our group is working to provide coordinates for key points so that the exercise science group can calculate valuable information.