Video based exercise recognition and correct pose detection

Rangari, Tushar; Kumar, Sudhanshu; Roy, Partha Pratim; Dogra, Debi Prosad; Kim, Byung-Gyu

doi:10.1007/s11042-022-12299-z

Cited by 25 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In its simplest form, such an analysis amounts to detecting whether the subject performs the exercise correctly or not. This was achieved several works [1,6,5] by exploiting 2D poses extracted from the input images. In particular, Dittakavi et al [5] detected which joints need to be fixed by finding the overall joint angle distribution of the dataset and detecting poses in which a joint angle is an anomaly.…”

Section: Physical Exercise Analysismentioning

confidence: 99%

“…While useful, such classification-based approaches offer limited information to the user, as they do not provide them with any feedback about the specific type of mistakes they made. Moreover, most of existing works operate on 2D pose inputs [1,2,3,6,5]. Similar to [4], we also design our framework to work with 3D poses enabling us to be robust to ambiguities found in 2D poses.…”

Section: Physical Exercise Analysismentioning

confidence: 99%

“…There is therefore a growing need for computer-aided exercise feedback strategies. A few recent works have addressed this problem [1,2,3,4,5,6]. However, they focus only on identifying whether an exercise is performed correctly or not [1,6], or they rely on hard-coded rules based on joint angles that cannot easily be extended to new exercises [2,3,4].…”

Section: Introductionmentioning

confidence: 99%

“…A few recent works have addressed this problem [1,2,3,4,5,6]. However, they focus only on identifying whether an exercise is performed correctly or not [1,6], or they rely on hard-coded rules based on joint angles that cannot easily be extended to new exercises [2,3,4]. In this work, we therefore leverage recent advances in the fields of pose estimation [7,8,9], action recognition [10,11] and motion prediction [12,13,14] to design a framework that provides automated and personalized feedback to supervise physical exercises.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

3D Pose Based Feedback for Physical Exercises

Zhao¹,

Kiciroglu²,

Hugues³

et al. 2022

Preprint

View full text Add to dashboard Cite

Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer individual training. Our framework does not rely on hard-coded, heuristic rules. Instead, it learns them from data, which facilitates its adaptation to specific user needs. To this end, we use a Graph Convolutional Network (GCN) architecture acting on the user's pose sequence to model the relationship between the the body joints trajectories. To evaluate our approach, we introduce a dataset with 3 different physical exercises. Our approach yields 90.9% mistake identification accuracy and successfully corrects 94.2% of the mistakes.

show abstract

Section: Physical Exercise Analysismentioning

confidence: 99%

Section: Physical Exercise Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3D Pose Based Feedback for Physical Exercises

Zhao¹,

Kiciroglu²,

Hugues³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Technology also makes telemedicine and remote monitoring capabilities possible. Healthcare professionals may remotely evaluate patients' exercise regimens using the exercise pose detection technology to ensure compliance and progress [18][26] [27] . Patients who may have trouble visiting healthcare institutions or need continual supervision owing to geographic restrictions might benefit notably from this remote monitoring option.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Elderly Wellness through AI- Powered Yoga and Exercise Support Systems

Adeyemi

2024

Preprint

View full text Add to dashboard Cite

This research presents a pioneering and comprehensive approach aimed at delivering personalized exercise and yoga support to the senior population. The primary objective of this research is to enhance physical well-being, boost engagement, foster adherence to exercise and yoga routines, and refine users' posture and balance. A pivotal phase in this project involves keypoint extraction, skillfully executed using MoveNet, an advanced posture estimation model. To achieve this, deep learning algorithms such as Convolutional Neural Networks (CNNs), Dense Neural Networks (DNNs), and Multi-Layer Perceptrons (MLPs) are deployed to effectively classify and categorize yoga and exercise positions. The culmination of this endeavor manifests in the form of an interactive web application. The robustness and efficacy of the system are underscored by extensive user testing, which has also assessed its usability and potential to significantly enhance the physical well-being of the elderly. In summation, this research represents a substantial advancement in the realm of targeted exercise and yoga support, expressly designed to cater to the distinctive needs of the senior demographic.

show abstract