2023
DOI: 10.3390/diagnostics13182881
|View full text |Cite
|
Sign up to set email alerts
|

Empowering Lower Limb Disorder Identification through PoseNet and Artificial Intelligence

Hafeez Ur Rehman Siddiqui,
Adil Ali Saleem,
Muhammad Amjad Raza
et al.

Abstract: A novel approach is presented in this study for the classification of lower limb disorders, with a specific emphasis on the knee, hip, and ankle. The research employs gait analysis and the extraction of PoseNet features from video data in order to effectively identify and categorize these disorders. The PoseNet algorithm facilitates the extraction of key body joint movements and positions from videos in a non-invasive and user-friendly manner, thereby offering a comprehensive representation of lower limb movem… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 57 publications
0
2
0
Order By: Relevance
“…For classification of exercises, the most commonly employed supervised ML models include the decision tree (DT) [31], the support vector machine (SVM) [31,42], the k-nearest neighbor (k-NN), and the random forest (RF) [21,31,42]. In recent years, deep learning (DL) techniques have shown outstanding performance in pattern recognition applications [21,51]. DL methods have been reported for the classification of various shoulder exercises, using either time series signals acquired from sensor data [21,32,33,39,42] or images captured by cameras.…”
Section: Artificial Intelligencementioning
confidence: 99%
“…For classification of exercises, the most commonly employed supervised ML models include the decision tree (DT) [31], the support vector machine (SVM) [31,42], the k-nearest neighbor (k-NN), and the random forest (RF) [21,31,42]. In recent years, deep learning (DL) techniques have shown outstanding performance in pattern recognition applications [21,51]. DL methods have been reported for the classification of various shoulder exercises, using either time series signals acquired from sensor data [21,32,33,39,42] or images captured by cameras.…”
Section: Artificial Intelligencementioning
confidence: 99%
“…To mitigate these shortcomings, recent years have witnessed the advent of gesture recognition methods grounded in hand pose estimation. For example, researchers leverage PoseNet networks to delineate hand poses through feature extraction and reverse inference of hand key points [18][19][20], thereby enhancing accuracy and robustness [21,22]. Additionally, approaches utilizing deep learning networks like ResNet-50 process feature maps to output heat maps of hand target joints, yielding commendable results in multi-target recognition [23].…”
Section: Introductionmentioning
confidence: 99%