MobiPhysio: A 2D video dataset of physiotherapy exercises for AI-driven assessment and monitoring.

Md Tauhid Bin Iqbal¹, Md Tawhid Mostafa², Md Tanvir Ahmed², Md Faiaz Fahim², Md Sagir Ahmed³, Anik Ahamad⁴, Khawja Redwanul Islam⁵, Byungyong Ryu⁶, Gihun Song⁷, Md Zahid Hossain⁸

¹Department of Computer Science and Engineering, East West University, Aftabnagar, Dhaka 1212, Bangladesh.

²Department of Computer Science and Engineering, Stamford University Bangladesh, Mughda, Dhaka 1214, Bangladesh.

³Augmedix, Tejgaon I/A, Dhaka 1208, Bangladesh.

⁴Digital Health, Deggendorf Institute of Technology, 94469 Deggendorf, Germany.

⁵University of Wales Trinity Saint David, Birmingham, 636A, United Kingdom.

⁶Meta Learn Inc., Hwaseong-si- 18469, South Korea.

⁷LG Electronics, AI Lab, Seoul- 06772, South Korea.

⁸Department of Physiotherapy and Rehabilitation, Jashore University of Science and Technology, Jashore 7408, Bangladesh.

PubMed PMC DOI PDF

Abstract

We present MobiPhysio, a 2D video-based dataset designed to support AI-driven physiotherapy assessment and monitoring. The dataset contains 3686 segmented videos of 9 Active Range of Motion physiotherapy exercises performed by 58 male and female participants. The recordings are done under the variations in lighting, camera angles, occlusion, and jitter in order to mimic real-world conditions. Data…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.