Preprint has been published in a journal as an article
DOI of the published article
Preprint / Version 2

A webcam-based machine learning approach for three-dimensional range of motion evaluation




Range of motion, Physical therapy, Rehabilitation, Machine learning, Computer vision, Pose estimation


Background. Joint range of motion (ROM) is an important quantitative measure for physical therapy. Commonly relying on a goniometer, accurate and reliable ROM measurement requires extensive training and practice. This, in turn, imposes a significant barrier for those who have limited in-person access to healthcare.

Objective. The current study presents and evaluates an alternative machine learning-based ROM evaluation method that could be remotely accessed via a webcam.

Methods. To evaluate its reliability, the ROM measurements for a diverse set of joints (neck, spine, and upper and lower extremities) derived using this method were compared to those obtained from a marker-based optical motion capture system.

Results. Data collected from 25 healthy adults demonstrated that the webcam solution exhibited high test-retest reliability, with substantial to almost perfect intraclass correlation coefficients for most joints. Compared with the marker-based system, the webcam-based system demonstrated substantial to almost perfect inter-rater reliability for some joints, and lower inter-rater reliability for other joints (e.g., shoulder flexion and elbow flexion), which could be attributed to the reduced sensitivity to joint locations at the apex of the movement.

Conclusions. The proposed webcam-based method exhibited high test-retest and inter-rater reliability, making it a versatile alternative for existing ROM evaluation methods in clinical practice and the tele-implementation of physical therapy and rehabilitation.


Metrics Loading ...


Garfan S, Alamoodi AH, Zaidan B, Al-Zobbi M, Hamid RA, Alwan JK, et al. Telehealth utilization during the Covid-19 pandemic: A systematic review. Comput Biol Med. 2021;138: 104878.

Snoswell CL, Chelberg G, De Guzman KR, Haydon HH, Thomas EE, Caffery LJ, et al. The clinical effectiveness of telehealth: a systematic review of meta-analyses from 2010 to 2019. J Telemed Telecare. 2021; 1–16.

Tsou C, Robinson S, Boyd J, Jamieson A, Blakeman R, Yeung J, et al. Effectiveness of Telehealth in Rural and Remote Emergency Departments: Systematic Review. J Med Internet Res. 2021;23: e30632. doi:10.2196/30632

Muir SW, Corea CL, Beaupre L. Evaluating change in clinical status: reliability and measures of agreement for the assessment of glenohumeral range of motion. North Am J Sports Phys Ther NAJSPT. 2010;5: 98.

Mullaney MJ, McHugh MP, Johnson CP, Tyler TF. Reliability of shoulder range of motion comparing a goniometer to a digital level. Physiother Theory Pract. 2010;26: 327–333.

Riddle DL, Rothstein JM, Lamb RL. Goniometric reliability in a clinical setting: shoulder measurements. Phys Ther. 1987;67: 668–673.

Rothstein JM, Miller PJ, Roettger RF. Goniometric reliability in a clinical setting: elbow and knee measurements. Phys Ther. 1983;63: 1611–1615.

van de Pol RJ, van Trijffel E, Lucas C. Inter-rater reliability for measurement of passive physiological range of motion of upper extremity joints is better if instruments are used: a systematic review. J Physiother. 2010;56: 7–17.

Meislin MA, Wagner ER, Shin AY. A comparison of elbow range of motion measurements: smartphone-based digital photography versus goniometric measurements. J Hand Surg. 2016;41: 510–515.

Li R, Jiang Q. A photogrammetric method for the measurement of three-dimensional cervical range of motion. IEEE J Biomed Health Inform. 2021.

Reese NB, Bandy WD. Joint range of motion and muscle length testing-E-book. Elsevier Health Sciences; 2016.

Kolber MJ, Hanney WJ. The reliability and concurrent validity of shoulder mobility measurements using a digital inclinometer and goniometer: a technical report. Int J Sports Phys Ther. 2012;7: 306–313.

Pérez-de la Cruz S, de León ÓA, Mallada NP, Rodríguez AV. Validity and intra-examiner reliability of the Hawk goniometer versus the universal goniometer for the measurement of range of motion of the glenohumeral joint. Med Eng Phys. 2021;89: 7–11.

Dent Jr PA, Wilke B, Terkonda S, Luther I, Shi GG. Validation of teleconference-based goniometry for measuring elbow joint range of motion. Cureus. 2020;12.

Feng M, Liang L, Sun W, Liu GW, Yin X, Han T, et al. Measurements of cervical range of motion using an optical motion capture system: Repeatability and validity. Exp Ther Med. 2019;18: 4193–4202.

Nagymáté G, Kiss RM. Application of OptiTrack motion capture systems in human movement analysis: A systematic literature review. Recent Innov Mechatron. 2018;5: 1–9.

Furtado JS, Liu HH, Lai G, Lacheray H, Desouza-Coelho J. Comparative analysis of optitrack motion capture systems. Advances in Motion Sensing and Control for Robotic Applications. Springer; 2019. pp. 15–31.

Toshev A, Szegedy C. Deeppose: Human pose estimation via deep neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. pp. 1653–1660.

Cao Z, Simon T, Wei S-E, Sheikh Y. Realtime multi-person 2d pose estimation using part affinity fields. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. pp. 7291–7299.

Mehta D, Sridhar S, Sotnychenko O, Rhodin H, Shafiei M, Seidel H-P, et al. Vnect: Real-time 3d human pose estimation with a single rgb camera. ACM Trans Graph TOG. 2017;36: 1–14.

Cejnog LWX, Cesar RM, de Campos TE, Elui VMC. Hand range of motion evaluation for Rheumatoid Arthritis patients. 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019). IEEE; 2019. pp. 1–5.

Wang J, Tan S, Zhen X, Xu S, Zheng F, He Z, et al. Deep 3D human pose estimation: A review. Comput Vis Image Underst. 2021;210: 103225. doi:10.1016/j.cviu.2021.103225

Lugaresi C, Tang J, Nash H, McClanahan C, Uboweja E, Hays M, et al. Mediapipe: A framework for building perception pipelines. ArXiv Prepr ArXiv190608172. 2019.

Bazarevsky V, Grishchenko I, Raveendran K, Zhu T, Zhang F, Grundmann M. BlazePose: On-device Real-time Body Pose tracking. CoRR. 2020;abs/2006.10204. Available:

Osokin D. Real-time 2d multi-person pose estimation on cpu: Lightweight openpose. ArXiv Prepr ArXiv181112004. 2018.

Kulikajevas A, Maskeliūnas R, Damaševičius R, Griškevičius J, Daunoravičienė K, Žižienė J, et al. Exercise Abnormality Detection Using BlazePose Skeleton Reconstruction. International Conference on Computational Science and Its Applications. Springer; 2021. pp. 90–104.

Young F, Mason R, Morris R, Stuart S, Godfrey A. Internet-of-Things-Enabled Markerless Running Gait Assessment from a Single Smartphone Camera. Sensors. 2023;23: 696.

Mittal N, Sabo A, Deshpande A, Clarke H, Taati B. Feasibility of video-based joint hypermobility assessment in individuals with suspected Ehlers-Danlos syndromes/generalised hypermobility spectrum disorders: a single-site observational study protocol. BMJ Open. 2022;12: e068098.

Mohammed SW, Garrapally V, Manchala S, Reddy SN, Naligenti SK. Recognition of Yoga Asana from Real-Time Videos using Blaze-pose. Int J Comput Digit Syst. 2022;5.

Rojas-Arce JL, Jimenez-Angeles L, Marmolejo-Saucedo JA. Telerehabilitation Prototype for Postural Disorder Monitoring in Parkinson Disease. International Conference on Computer Science and Health Engineering. Springer; 2021. pp. 129–142.

Singha RG, Lad M, Shipurkar GM, Rohekar A, Chauhan C, Rathod N. Dynamic Pose Diagnosis with BlazePose and LSTM for Spinal Dysfunction Risk Estimation. 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE; 2022. pp. 1547–1552.

Fan J, Gu F, Lv L, Zhang Z, Zhu C, Qi J, et al. Reliability of a human pose tracking algorithm for measuring upper limb joints: comparison with photography-based goniometry. BMC Musculoskelet Disord. 2022;23: 1–10.

Bradski G. The OpenCV Library. Dr Dobbs J Softw Tools. 2000.

Kluwak K, Klempous R, Chaczko Z, Rozenblit JW, Kulbacki M. People Lifting Patterns—A Reference Dataset for Practitioners. Sensors. 2021;21: 3142. doi:10.3390/s21093142

Range of Joint Motion Evaluation Chart. 2014. Available:

Wang XM, Welsh TN. TAT-HUM: Trajectory Analysis Toolkit for Human Movements in Python. PsyArXiv; 2023. doi:10.31234/

Harry JR, Blinch J, Barker LA, Krzyszkowski J, Chowning L. Low-pass filter effects on metrics of countermovement vertical jump performance. J Strength Cond Res. 2022;36: 1459–1467.

Schreven S, Beek PJ, Smeets JB. Optimising filtering parameters for a 3D motion analysis system. J Electromyogr Kinesiol. 2015;25: 808–814.

Seabold S, Perktold J. statsmodels: Econometric and statistical modeling with python. 9th Python in Science Conference. 2010.

McGraw KO, Wong SP. Forming inferences about some intraclass correlation coefficients. Psychol Methods. 1996;1: 30.

Koo TK, Li MY. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med. 2016;15: 155–163.

Wolak ME, Fairbairn DJ, Paulsen YR. Guidelines for Estimating Repeatability. Methods Ecol Evol. 2012;3: 129–137.

Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977; 159–174.

Stratford PW, Goldsmith CH. Use of the standard error as a reliability index of interest: an applied example using elbow flexor strength data. Phys Ther. 1997;77: 745–750.

Hall T, Briffa K, Hopper D, Robinson K. Long-term stability and minimal detectable change of the cervical flexion-rotation test. J Orthop Sports Phys Ther. 2010;40: 225–229.

Perez-Grau F, Ragel R, Caballero F, Viguria A, Ollero A. Semi-autonomous teleoperation of UAVs in search and rescue scenarios. 2017 International Conference on Unmanned Aircraft Systems (ICUAS). IEEE; 2017. pp. 1066–1074.

Gesture recognition task guide | MediaPipe | Google for Developers. [cited 31 Jul 2023]. Available:



2022-11-14 — Updated on 2023-10-31