Limb Prescribe: Text-to-Pose Generative Model for Therapeutic Exercise Prescription
Date of Award
4-30-2024
Document Type
Thesis
Degree Name
Master of Science in Computer Vision
Department
Computer Vision
First Advisor
Prof. Mohammad Yaqub
Second Advisor
Prof. Karthik Nandakumar
Abstract
Despite physical therapy's significant impact on improving quality of life, its high cost often renders it a luxury. This thesis focuses on "Limb Prescribe: Text-to-Pose Generative Model for Therapeutic Exercise Prescription," which aims to make physiotherapy more accessible. Our research began by understanding the domain and identifying areas where AI could add value through multidisciplinary frameworks. We developed Limb Prescribe to address the customization needs of therapeutic exercises. In physiotherapy, each case is unique, with specific needs and constraints. Limb Prescribe is a text-to-pose generative model designed for therapeutic exercise prescriptions. By integrating pose initialization, iterative pose generation based on previous poses, and incorporating physical constraints, we enhance the model's suitability for exercise prescription. Feedback from fifteen physiotherapists confirmed the model's potential, highlighting the need for further development.
Recommended Citation
S. Alsaedi, "Limb Prescribe: Text-to-Pose Generative Model for Therapeutic Exercise Prescription,", Apr 2024.
Comments
Thesis submitted to the Deanship of Graduate and Postdoctoral Studies
In partial fulfilment of the requirements for the M.Sc degree in Computer Vision
Advisors:Hisham Cholakkal, Abdulmotaleb Elsaddik
with 2 years embargo period