Title: REST – Software for home-based REhabilitation of STroke survivors
Funding source: FNR Pathfinder
Project manager: Dr. Djamila Aouada
Principal investigator: Dr. Enjie Ghorbal
Researchers: Renato Baptista, Dr.Abd El Rahman Shabayek
Starting date/ Duration: 01/01/2020 – 4 months

logo

Rehabilitation is considered as an essential step in the recovery process of stroke survivors. Nevertheless, due to the economical burden, patients can benefit from an on-site rehabilitation only for a limited period. To motivate the patient, provide him with assistance and avoid musculoskeletal injuries when exercising alone, we propose a new solution allowing patients to safely exercise at the comfort of their homes. This solution has been initially developed in the context EU H2020 project “STARR”.  It consists in a home-based rehabilitation system composed of two linked applications. The first application enables the therapist to remotely prescribe exercises tailored to the patient’s condition and control his training. The second application allows the patient to receive his prescription and experience an instantaneous visual feedback while training at the comfort of his home. The project “REST” aims at studying the potential of this application in the market. This funding has been obtained under the FNR call “JUMP Pathfinder 2019-2.

TEST

A dataset containing 400 real, high-resolution human scans of 200 subjects (100 males and 100 females in two poses each) with high-quality texture and their corresponding low-resolution meshes, with automatically computed ground-truth correspondences. See the following table.

TEST

A dataset containing 400 real, high-resolution human scans of 200 subjects (100 males and 100 females in two poses each) with high-quality texture and their corresponding low-resolution meshes, with automatically computed ground-truth correspondences. See the following table.

TEST

A dataset containing 400 real, high-resolution human scans of 200 subjects (100 males and 100 females in two poses each) with high-quality texture and their corresponding low-resolution meshes, with automatically computed ground-truth correspondences. See the following table.

TEST

A dataset containing 400 real, high-resolution human scans of 200 subjects (100 males and 100 females in two poses each) with high-quality texture and their corresponding low-resolution meshes, with automatically computed ground-truth correspondences. See the following table.