University of Twente Student Theses

Login

Analysing Real-Time Vision-Based Pose Estimation Algorithms for RITH Purposes on Embedded Devices

Popovici, Andrei (2022) Analysing Real-Time Vision-Based Pose Estimation Algorithms for RITH Purposes on Embedded Devices.

[img] PDF
3MB
Abstract:Rehabilitation programs are vital for the people that suffer injuries. The Covid-19 pandemic made it impossible for these people to follow such programs at healthcare centers. This study aims to develop a new solution for patients opting instead for a Rehabilitation in the Home (RITH) program. The proposed approach is divided into two phases. Firstly, the app tracks and extracts the 2D coordinates of the joints. The second phase uses these extracted coordinates to guide the patient during the exercise. All captured frames are compared to the reference frames, and their similarity is computed. Developing a home-based rehabilitation helper that will work on low-resource devices will bring benefits, including decreased travel time and flexible exercise hours for patients.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:https://purl.utwente.nl/essays/91810
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page