Kinect-Based Physiotherapy and Assessment: A Comprehensive Review

Rashid, Fadilla ‘Atyka Nor; Suriani, Nor Surayahani; Nazari, Ain

doi:10.11591/ijeecs.v11.i3.pp1176-1187

Cited by 13 publications

(5 citation statements)

References 55 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More importantly, a maximum of six spatial points was required to estimate the eight motion angles of the upper limb. The locations of the six spatial points coincided with those of Kinect's human skeleton recognition technology 33 , which encourages the application of P-BTBS to most scenarios for estimating the spatial coordinates.…”

Section: Resultsmentioning

confidence: 62%

“…26 , 27 , solving upper-limb joint motion angles 28 – 30 , combining sliding mode control algorithms for human–machine interaction 31 , applying Kalman filtering techniques to fuse multiple Kinect data and track human motion 32 , etc. While Kinect’s human skeleton recognition technology offers the advantages of high flexibility, low cost, and non-invasiveness 33 , the number of human joint spatial points identified and extracted from the upper limb is very limited. Innovative approaches (multi-camera data fusion 32 and inertial sensor compensation 34 , 35 ) and wearable devices 36 – 38 have been developed to improve the accuracy of Kinect depth camera data and measure upper-limb motion angles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Upper limb modeling and motion extraction based on multi-space-fusion

Wang,

Guo,

Pei

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Modeling and motion extraction of human upper limbs are essential for interpreting the natural behavior of upper limb. Owing to the high degrees of freedom (DOF) and highly dynamic nature, existing upper limb modeling methods have limited applications. This study proposes a generic modeling and motion extraction method, named Primitive-Based triangular body segment method (P-BTBS), which follows the physiology of upper limbs, allows high accuracy of motion angles, and describes upper-limb motions with high accuracy. For utilizing the upper-limb modular motion model, the motion angles and bones can be selected as per the research topics (The generic nature of the study targets). Additionally, P-BTBS is suitable in most scenarios for estimating spatial coordinates (The generic nature of equipment and technology). Experiments in continuous motions with seven DOFs and upper-limb motion description validated the excellent performance and robustness of P-BTBS in extracting motion information and describing upper-limb motions, respectively. P-BTBS provides a new perspective and mathematical tool for human understanding and exploration of upper-limb motions, which theoretically supports upper-limb research.

show abstract

Section: Resultsmentioning

confidence: 62%

Section: Introductionmentioning

confidence: 99%

Upper limb modeling and motion extraction based on multi-space-fusion

Wang,

Guo,

Pei

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The application of Kinect-based rehabilitation as a low-cost and flexible method is rapidly expanding [ 15 ]. Kinect contains an RGB camera (R for red, G for green, and B for blue), a depth sensor, and a layer of microphones to record body movements and detect faces and voices [ 16 ]. Microsoft Kinect is a markless motion capture system that presents innovative and exciting methods for offering a more enjoyable treatment and promoting motivation in and adherence to the treatment [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

Kinect-Based Rehabilitation Systems for Stroke Patients: A Scoping Review

Almasi

Ahmadi

Asadi

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Background and Objective. Kinect-based rehabilitation is an effective solution for creating motivation and promoting adherence to rehabilitation programs in stroke patients. The current study was aimed at examining the effects of Kinect-based rehabilitation systems on performance improvement, domains of use, and its limitations for stroke patients. Method. This study was conducted according to Arksey and O’Malley’s framework. To investigate the evidence on the effects of Kinect-based rehabilitation, a search was executed in five databases (Web of Science, PubMed, Cochrane Library, Scopus, and IEEE) from 2010 to 2020. Results. Thirty-three articles were finally selected by the inclusion criteria. Most of the studies had been conducted in the US (22%). In terms of the application of Kinect-based rehabilitation for stroke patients, most studies had focused on the rehabilitation of upper extremities (55%), followed by balance (27%). The majority of the studies had developed customized rehabilitation programs (36%) for the rehabilitation of stroke patients. Most of these studies had noted that the simultaneous use of Kinect-based rehabilitation and other physiotherapy methods has a more noticeable effect on performance improvement in patients. Conclusion. The simultaneous application of Kinect-based rehabilitation and other physiotherapy methods has a stronger effect on the performance improvement of stroke patients. Better effects can be achieved by designing Kinect-based rehabilitation programs tailored to the characteristics and abilities of stroke patients.

show abstract

“…Video data offer the potential ability to measure the movement of the entire body. Existing platforms often rely on specialized hardware (e.g., Microsoft Kinect [ 23 ]) or costly motion capture systems [ 24 ]. In particular, support vector machines (SVM) have been trained on keypoints obtained from Microsoft Kinect systems for emotion and gesture recognition [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Physiotherapy Exercise Classification with Single-Camera Pose Detection and Machine Learning

Arrowsmith

Burns

Mak³

et al. 2022

Sensors

View full text Add to dashboard Cite

Access to healthcare, including physiotherapy, is increasingly occurring through virtual formats. At-home adherence to physical therapy programs is often poor and few tools exist to objectively measure participation. The aim of this study was to develop and evaluate the potential for performing automatic, unsupervised video-based monitoring of at-home low-back and shoulder physiotherapy exercises using a mobile phone camera. Joint locations were extracted from the videos of healthy subjects performing low-back and shoulder physiotherapy exercises using an open source pose detection framework. A convolutional neural network was trained to classify physiotherapy exercises based on the segments of keypoint time series data. The model’s performance as a function of input keypoint combinations was studied in addition to its robustness to variation in the camera angle. The CNN model achieved optimal performance using a total of 12 pose estimation landmarks from the upper and lower body (low-back exercise classification: 0.995 ± 0.009; shoulder exercise classification: 0.963 ± 0.020). Training the CNN on a variety of angles was found to be effective in making the model robust to variations in video filming angle. This study demonstrates the feasibility of using a smartphone camera and a supervised machine learning model to effectively classify at-home physiotherapy participation and could provide a low-cost, scalable method for tracking adherence to physical therapy exercise programs in a variety of settings.

show abstract

Kinect-Based Physiotherapy and Assessment: A Comprehensive Review

Cited by 13 publications

References 55 publications

Upper limb modeling and motion extraction based on multi-space-fusion

Upper limb modeling and motion extraction based on multi-space-fusion

Kinect-Based Rehabilitation Systems for Stroke Patients: A Scoping Review

Physiotherapy Exercise Classification with Single-Camera Pose Detection and Machine Learning

Contact Info

Product

Resources

About