Evaluating Kinect, OpenPose and BlazePose for Human Body Movement Analysis on a Low Back Pain Physical Rehabilitation Dataset - Université de Bretagne Occidentale
Conference Papers Year : 2023

Evaluating Kinect, OpenPose and BlazePose for Human Body Movement Analysis on a Low Back Pain Physical Rehabilitation Dataset

Abstract

Analyzing human motion is an active research area, with various applications. In this work, we focus on human motion analysis in the context of physical rehabilitation using a robot coach system. Computer-aided assessment of physical rehabilitation entails evaluation of patient performance in completing prescribed rehabilitation exercises, based on processing movement data captured with a sensory system, such as RGB and RGB-D cameras. As 2D and 3D human pose estimation from RGB images had made impressive improvements, we aim to compare the assessment of physical rehabilitation exercises using movement data obtained from both RGB-D camera (Microsoft Kinect) and estimation from RGB videos (OpenPose and BlazePose algorithms). A Gaussian Mixture Model (GMM) is employed from position (and orientation) features, with performance metrics defined based on the log-likelihood values from GMM. The evaluation is performed on a medical database of clinical patients carrying out low back-pain rehabilitation exercises, previously coached by robot Poppy.
Fichier principal
Vignette du fichier
Marusic2023C2AICHI.pdf (4.8 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04133691 , version 1 (05-08-2024)

Licence

Identifiers

Cite

Aleksa Marusic, Sao Mai Nguyen, Adriana Tapus. Evaluating Kinect, OpenPose and BlazePose for Human Body Movement Analysis on a Low Back Pain Physical Rehabilitation Dataset. 18th ACM/IEEE International Conference on Human-Robot Interaction (HRI 2023), Mar 2023, Stockholm, Sweden. pp.587-591, ⟨10.1145/3568294.3580153⟩. ⟨hal-04133691⟩
117 View
8 Download

Altmetric

Share

More