Reliability and validity analysis of MediaPipe-based measurement system for some human rehabilitation motions

Latreche, Ameur; Kelaiaia, Ridha; Chemori, Ahmed; Kerboua, Adlen

doi:10.1016/j.measurement.2023.112826

Cited by 23 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their findings were consistent with both X-ray and goniometry measurements (ICC range: 0.963-0.994) [59]. Also, Latreche et al [60] confirmed the valid results of MediaPipe for specific rehabilitation movements. They reported ICC values of 0.96, 0.99, 0.99, and 0.99 for shoulder abduction, adduction, extension, and flexion movements, respectively.…”

Section: Discussionsupporting

confidence: 72%

Biomechanical Posture Analysis in Healthy Adults with Machine Learning: Applicability and Reliability

Roggio,

Di Grande,

Cavalieri

et al. 2024

Sensors

View full text Add to dashboard Cite

Posture analysis is important in musculoskeletal disorder prevention but relies on subjective assessment. This study investigates the applicability and reliability of a machine learning (ML) pose estimation model for the human posture assessment, while also exploring the underlying structure of the data through principal component and cluster analyses. A cohort of 200 healthy individuals with a mean age of 24.4 ± 4.2 years was photographed from the frontal, dorsal, and lateral views. We used Student’s t-test and Cohen’s effect size (d) to identify gender-specific postural differences and used the Intraclass Correlation Coefficient (ICC) to assess the reliability of this method. Our findings demonstrate distinct sex differences in shoulder adduction angle (men: 16.1° ± 1.9°, women: 14.1° ± 1.5°, d = 1.14) and hip adduction angle (men: 9.9° ± 2.2°, women: 6.7° ± 1.5°, d = 1.67), with no significant differences in horizontal inclinations. ICC analysis, with the highest value of 0.95, confirms the reliability of the approach. Principal component and clustering analyses revealed potential new patterns in postural analysis such as significant differences in shoulder–hip distance, highlighting the potential of unsupervised ML for objective posture analysis, offering a promising non-invasive method for rapid, reliable screening in physical therapy, ergonomics, and sports.

show abstract

Section: Discussionsupporting

confidence: 72%

Biomechanical Posture Analysis in Healthy Adults with Machine Learning: Applicability and Reliability

Roggio,

Di Grande,

Cavalieri

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…MediaPipe was also used in a study by Latreche et al to achieve a 95% agreement with the goniometer result by physical therapists in terms of reliability and validity. Therefore, it was determined to be suitable for use in developing the program in this study [ 20 , 21 ].…”

Section: Methodsmentioning

confidence: 99%

“…As an alternative, marker-less motion analysis systems with devices such as the Kinect camera have been developed. The recent advancement of artificial intelligence (AI) technology has enabled real-time motion analysis solely using a webcam or a mobile phone camera [ 18 , 19 , 20 , 21 ]. Despite technological advancements, only a few studies have explored the use of AI technology in the rehabilitation exercises of subjects with SCI.…”

Section: Introductionmentioning

confidence: 99%

Development and Validation of an Artificial Intelligence-Based Motion Analysis System for Upper Extremity Rehabilitation Exercises in Patients with Spinal Cord Injury: A Randomized Controlled Trial

Lee,

Jin,

Kim

et al. 2023

Healthcare

View full text Add to dashboard Cite

In this study, we developed an AI-based real-time motion feedback system for patients with spinal cord injury (SCI) during rehabilitation, aiming to enhance their interest and motivation. The effectiveness of the system in improving upper-limb muscle strength during the Thera band exercises was evaluated. The motion analysis program, including exercise repetition counts and calorie consumption, was developed using MediaPipe, focusing on three key motions (chest press, shoulder press, and arm curl) for upper extremity exercises. The participants with SCI were randomly assigned to the experimental group (EG = 4) or control group (CG = 5), engaging in 1 h sessions three times a week for 8 weeks. Muscle strength tests (chest press, shoulder press, lat pull-down, and arm curl) were performed before and after exercises. Although both groups did not show significant differences, the EG group exhibited increased strength in all measured variables, whereas the CG group showed constant or reduced results. Consequently, the computer program-based system developed in this study could be effective in muscle strengthening. Furthermore, these findings may serve as a valuable foundation for future AI-driven rehabilitation exercise systems.

show abstract

“…Therefore, it is necessary to preprocess the gesture image. Mediapipe is a cross-platform and open-source machine learning framework developed by Google, which contains visual algorithm models for image classification, face detection, and gesture recognition [21]. The preprocessing method is mainly to use the Mediapipe gesture recognition model to detect gestures and locate key points on the images.…”

Section: Attention Mechanismmentioning

confidence: 99%

Research on gesture segmentation method based on FCN combined with CBAM-ResNet50

ZHAO,

LIANG,

2024

Preprint

View full text Add to dashboard Cite

As a key step of gesture recognition, gesture segmentation can effectively reduce the impact of complex backgrounds on recognition results and improve the accuracy of gesture recognition. The gesture segmentation algorithm based on image processing is easily affected by the complex backgrounds in the image, resulting in poor gesture segmentation effect and low precision. To improve the effect of gesture segmentation under complex backgrounds, this paper proposes a gesture segmentation method based on FCN combined with the CBAM-ResNet50 network model. The trunk network of FCN is proposed as a new ResNet-50 framework. CBAM attention mechanism is introduced into the residual structure to enhance the extraction ability of multi-scale context information. And we achieve deep feature and shallow feature extraction and fusion by combining expansion convolution and enhancing the parameters of the convolutional layer, so as to improve the precision of gesture segmentation. In addition, the methods of data preprocessing and loading pre-training weights are used to enhance the model’s robustness and performance and expedite the training time. In the experiments, the NUS-II gesture data set with a complex background was used for testing. The average recognition rate of gesture pixels was 97.41% and gesture IoU was 94.54%. The experimental results show that the proposed method has a good effect on gesture segmentation for gesture images with complex backgrounds.

show abstract

Reliability and validity analysis of MediaPipe-based measurement system for some human rehabilitation motions

Cited by 23 publications

References 35 publications

Biomechanical Posture Analysis in Healthy Adults with Machine Learning: Applicability and Reliability

Biomechanical Posture Analysis in Healthy Adults with Machine Learning: Applicability and Reliability

Development and Validation of an Artificial Intelligence-Based Motion Analysis System for Upper Extremity Rehabilitation Exercises in Patients with Spinal Cord Injury: A Randomized Controlled Trial

Research on gesture segmentation method based on FCN combined with CBAM-ResNet50

Contact Info

Product

Resources

About