Subject

Gait analysis assesses the gait capabilities of a subject by quantifying different parameters, for instance the joint angles. It is usually performed using marker-based systems such as Vicon, in which multiple cameras track markers placed on the subject’s body. Marker based systems are therefore not portable and are difficult to use. Instead, the Kinect RGBD sensor offers a marker less, cheap, portable solution to track the subject body. Nevertheless, Kinect is limited by its inherent inaccuracy and the measured joint angles are generally not enough accurate for clinical assessment.

Kind of work

The objective of this master thesis is to refine the joint angles measured by Kinect using a deep learning approach. Such deep learning model is trained using Kinect joint angles as the input and Vicon joint angles as targets. The data will be collected by the student in the Brubotics Rehabilitation Research Center.