Deep Learning for Fitness
- URL: http://arxiv.org/abs/2109.01376v1
- Date: Fri, 3 Sep 2021 08:42:07 GMT
- Title: Deep Learning for Fitness
- Authors: Mahendran N
- Abstract summary: Fitness tutor is an application for maintaining correct posture during workout exercises or doing yoga.
Inspired by healthcare innovations like robotic surgery, we design a novel application Fitness tutor which can guide the workouts using pose estimation.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: We present Fitness tutor, an application for maintaining correct posture
during workout exercises or doing yoga. Current work on fitness focuses on
suggesting food supplements, accessing workouts, workout wearables does a great
job in improving the fitness. Meanwhile, the current situation is making
difficult to monitor workouts by trainee. Inspired by healthcare innovations
like robotic surgery, we design a novel application Fitness tutor which can
guide the workouts using pose estimation. Pose estimation can be deployed on
the reference image for gathering data and guide the user with the data. This
allow Fitness tutor to guide the workouts (both exercise and yoga) in remote
conditions with a single reference posture as image. We use posenet model in
tensorflow with p5js for developing skeleton. Fitness tutor is an application
of pose estimation model in bringing a realtime teaching experience in fitness.
Our experiments shows that it can leverage potential of pose estimation models
by providing guidance in realtime.
Related papers
- Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations [62.132347451049455]
Scale has become a main ingredient in obtaining strong machine learning models.
In this work, we argue that scale and training research has been needlessly complex due to reliance on the cosine schedule.
We show that weight averaging yields improved performance along the training trajectory, without additional training costs, across different scales.
arXiv Detail & Related papers (2024-05-28T17:33:54Z) - A Spatial-Temporal Transformer based Framework For Human Pose Assessment
And Correction in Education Scenarios [6.146739983645156]
The framework comprises skeletal tracking, pose estimation, posture assessment, and posture correction modules.
We create a pose correction method to provide corrective feedback in the form of visual aids.
Results show that our model can effectively measure and comment on the quality of students' actions.
arXiv Detail & Related papers (2023-11-01T09:53:38Z) - Using Learnable Physics for Real-Time Exercise Form Recommendations [2.1548132286330453]
We present an algorithmic pipeline that can diagnose problems in exercise techniques and offer corrective recommendations.
We use MediaPipe for pose recognition, count repetitions using peak-prominence detection, and use a learnable physics simulator to track motion evolution.
arXiv Detail & Related papers (2023-10-11T06:11:11Z) - 3D Pose Based Feedback for Physical Exercises [87.35086507661227]
We introduce a learning-based framework that identifies the mistakes made by a user.
Our framework does not rely on hard-coded rules, instead, it learns them from data.
Our approach yields 90.9% mistake identification accuracy and successfully corrects 94.2% of the mistakes.
arXiv Detail & Related papers (2022-08-05T16:15:02Z) - Muscle Vision: Real Time Keypoint Based Pose Classification of Physical
Exercises [52.77024349608834]
3D human pose recognition extrapolated from video has advanced to the point of enabling real-time software applications.
We propose a new machine learning pipeline and web interface that performs human pose recognition on a live video feed to detect when common exercises are performed and classify them accordingly.
arXiv Detail & Related papers (2022-03-23T00:55:07Z) - Domain Knowledge-Informed Self-Supervised Representations for Workout
Form Assessment [12.040334568268445]
We propose to learn exercise-specific representations from unlabeled samples.
In particular, our domain knowledge-informed self-supervised approaches exploit the harmonic motion of the exercise actions.
We show that our self-supervised representations outperform off-the-shelf 2D- and 3D-pose estimators.
arXiv Detail & Related papers (2022-02-28T18:40:02Z) - Imposing Temporal Consistency on Deep Monocular Body Shape and Pose
Estimation [67.23327074124855]
This paper presents an elegant solution for the integration of temporal constraints in the fitting process.
We derive parameters of a sequence of body models, representing shape and motion of a person, including jaw poses, facial expressions, and finger poses.
Our approach enables the derivation of realistic 3D body models from image sequences, including facial expression and articulated hands.
arXiv Detail & Related papers (2022-02-07T11:11:55Z) - LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human
Bodies [78.17425779503047]
We propose a novel neural implicit representation for the human body.
It is fully differentiable and optimizable with disentangled shape and pose latent spaces.
Our model can be trained and fine-tuned directly on non-watertight raw data with well-designed losses.
arXiv Detail & Related papers (2021-11-30T04:10:57Z) - FixMyPose: Pose Correctional Captioning and Retrieval [67.20888060019028]
We introduce a new captioning dataset named FixMyPose to address automated pose correction systems.
We collect descriptions of correcting a "current" pose to look like a "target" pose.
To avoid ML biases, we maintain a balance across characters with diverse demographics.
arXiv Detail & Related papers (2021-04-04T21:45:44Z) - Pose Trainer: Correcting Exercise Posture using Pose Estimation [7.005458308454871]
Pose Trainer is an application that detects the user's exercise pose and provides personalized, detailed recommendations on how the user can improve their form.
We record a dataset of over 100 exercise videos of correct and incorrect form, based on personal training guidelines, and build geometric-heuristic and machine learning algorithms for evaluation.
arXiv Detail & Related papers (2020-06-21T05:51:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.