IRJET- A Review of Machine Learning Technique for Yoga Posture Classification (original) (raw)
Related papers
YOGA POSE DETECTION USING MACHINE LEARNING LIBRARIES
IRJET, 2022
Over many years yoga has been the source of energy and enlightment. The existence of yoga traces back to India, over 5000 years ago. Yoga is derived from a Sankrit root word "Yuj" which means "to join", "to yoke" or "to unite". All through the years yoga has been practiced for various reasons. Our aim is to come up with solutions of how to help people in the formation of yoga poses with accuracy. Along with this our focus is to solve the problem of having an instructor, in order to perform yoga. The project aims at designing a system that can detect a yoga performer's pose in real-time and predict whether he/she is doing it correctly or not. We plan on accurately predicting five popular yoga poses namely, downward dog, plank pose, tree pose, goddess pose and warrior-2 pose. This would involve training a Machine Learning model to complete the required task. OpenCV would be used for handling the images and pose detection will be performed using MediaPipe. A web application will be developed providing the user with a platform to easily perform his task with ease.
AI Human Pose Estimation: Yoga Pose Detection and Correction
CERN European Organization for Nuclear Research - Zenodo, 2022
The most important of yoga poses is known around the world and proves the health benefits preached by ancient sages. As yoga becomes more important, yoga faces the following important challenges: Computer vision technology provides a promising solution for assessing human posture. However, these techniques are rarely used in the areas of health and exercise, and there are no specific references or projects. Named after yoga. This white paper describes the different technologies that can be used for pose estimation and summarize the best ways to use them based on the ease of use of your Android app application. The following describes the methodology used to provide yoga pose estimation in Android applications, how the app is modelled, and how each component works. Pose estimation is a branch of computer vision that deals with the recognition of the individual parts that make up the body (usually the human body). There are several ways to achieve this, The approach I use starts with passing the incoming image through a CNN classifier trained to look for people. When the human body poses are recognized, the pose estimation network searches for trained joints and limbs. The computer can then display the image to the user using markers that identify parts of the body.
Yoga Pose Detection and Classification Using Deep Learning
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2020
Yoga is an ancient science and discipline originated in India 5000 years ago. It is used to bring harmony to both body and mind with the help of asana, meditation and various other breathing techniques It bring peace to the mind. Due to increase of stress in the modern lifestyle, yoga has become popular throughout the world. There are various ways through which one can learn yoga. Yoga can be learnt by attending classes at a yoga centre or through home tutoring. It can also be self-learnt with the help of books and videos. Most people prefer self-learning but it is hard for them to find incorrect parts of their yoga poses by themselves. Using the system, the user can select the pose that he/she wishes to practice. He/she can then upload a photo of themselves doing the pose. The pose of the user is compared with the pose of the expert and difference in angles of various body joints is calculated. Based on thisdifference of angles feedback is provided to the user so that he/she can improve the pose.
PeerJ Computer Science
Virtual motion and pose from images and video can be estimated by detecting body joints and their interconnection. The human body has diverse and complicated poses in yoga, making its classification challenging. This study estimates yoga poses from the images using a neural network. Five different yoga poses, viz. downdog, tree, plank, warrior2, and goddess in the form of RGB images are used as the target inputs. The BlazePose model was used to localize the body joints of the yoga poses. It detected a maximum of 33 body joints, referred to as keypoints, covering almost all the body parts. Keypoints achieved from the model are considered as predicted joint locations. True keypoints, as the ground truth body joint for individual yoga poses, are identified manually using the open source image annotation tool named Makesense AI. A detailed analysis of the body joint detection accuracy is proposed in the form of percentage of corrected keypoints (PCK) and percentage of detected joints (P...
YoNet: A Neural Network for Yoga Pose Classification
SN Computer Science
Yoga has become an integral part of human life to maintain a healthy body and mind in recent times. With the growing, fast-paced life and work from home, it has become difficult for people to invest time in the gymnasium for exercises. Instead, they like to do assisted exercises at home where pose recognition techniques play the most vital role. Recognition of different poses is challenging due to proper dataset and classification architecture. In this work, we have proposed a deep learning-based model to identify five different yoga poses from comparatively fewer amounts of data. We have compared our model’s performance with some state-of-the-art image classification models-ResNet, InceptionNet, InceptionResNet, Xception and found our architecture superior. Our proposed architecture extracts spatial, and depth features from the image individually and considers them for further calculation in classification. The experimental results show that it achieved 94.91% accuracy with 95.61% ...
Yoga pose annotation and classification by using timedistributed convolutional neural network
Indonesian Journal of Electrical Engineering and Computer Science, 2023
In India, people have been practicing yoga for thousands of years to improve their health and well-being on all levels. As the pace of technological development increases, this presents a great opening for computational probing across all areas of social domains. Nevertheless, it remains difficult to integrate artificial intelligence (AI) and machine learning (ML) methods to an interdisciplinary field like yoga. The proposed study aims to develop a yoga pose annotation and classification for yogasana recognition in real time. The study considers TensorFlow for better implementation of data automation, performance monitoring. TensorFlow yields better numerical computation and hat helps ML and efficiently develops the neural network. The proposed composed of time-distributed convolutional neural network (CNN) through the Softmax function. Also, a poseNet algorithm is considered to estimate the user's real-time yoga pose. The use of a database i.e., poseTrack in the proposed method offers annotation to the evaluation of yoga pose and tracking of it. The performance analysis of the proposed yoga pose annotation and classification model suggests that it offers higher accuracy than traditional, support vector machines (SVM) and K-nearest neighbor (KNN).
Aasna: Kinematic Yoga Posture Detection And Correction System Using CNN
ITM Web of Conferences
Yoga is a very popular form of exercise that originated in India that has numerous benefits for the mind and body. According to recent statistics, there are over 300 million yoga practitioners worldwide, with the number of yoga instructors increasing annually. However, incorrect yoga postures can lead to injuries and health complications. This highlights the importance of correct yoga posture and the need for a system that can detect and correct improper poses. This abstract presents a yoga posture detection and correction system designed using OpenCV for computer vision, and kinematic representation of the human body considering 17 points mapped on the human body, utilizing the tf-pose estimation algorithm for precise pose estimation. The system also includes a convolutional neural network (CNN) model developed using the Keras API and trained on the TensorFlow platform's MoveNet architecture for handling training of the model. The MoveNet pose estimation module has been used to...
The computerized Self-training Artificial intelligence structures for sports and fitness can advance participant performance and thwart damages. Concocting an interactive web application that uses the webcam to recognize the user's yoga and exercise poses, and estimates each pose to assist the user practicing those postures and tracks successful shots at various stances. Our approach seeks to recognize the yoga asanas based on the data attained by Data Collection from an open-source dataset. The sensed critical points are conceded to our prototype where neural networks find patterns and Sequential model-CNN analyze their evolution over time. Mediapipe framework is used in detecting the landmarks of the human body to retrieve the stick figure of the user for estimating their yoga poses and predict its accuracy by passing it to the CNN model. Finally, the system contains a meditation coach which is programmed to give commands at standard intervals and subsequently, the user is ushered by a voice that instructs them to maintain their breathing pace thereby creating a soothing environment.
Yoga Pose Detection and Correction using Posenet and KNN
The fundamental goal of Yoga pose detection and correction is to provide standard and correct yoga postures using computer vision. If the yoga posture is not done properly, it can result in serious injuries and long-term issues. Analyzing human poses to detect and correct yoga poses can benefit humans living a healthier life in their homely environment. This project focuses on exploring the different approaches for yoga pose classification, so we are using PoseNet and KNN classifier. Using such deep learning algorithms, an individual can get the correct/ideal way/method to perform that specific yoga asana that he/she is trying to do. Using computer vision techniques and Open Pose (an open-source library), human pose estimation is used to estimate an individual's Yoga posture. The suggested system recognises the difference between the actual and target positions and corrects the user with high accuracy by offering real-time visual output and necessary instructions to correct the identified pose.
AI-Based Yoga Pose Estimation for Android Application
Volume 5 - 2020, Issue 9 - September, 2020
The importance of yoga is renowned worldwide and its health benefits, which were preached by ancient sages, have stood the test of time. Even though yoga is becoming preeminent, there are important challenges faced while doing yoga such as performing it with incorrect form, the classes being expensive and the shortage of time in our busy lives. Computer vision techniques exhibit promising solutions for human pose estimation. However, these techniques are seldom applied in the domain of health or exercise, with no literature or projects cited specifically for yoga. This paper surveys the various technologies that can be used for pose estimation and concludes the best method based on the usability for an android application. The paper then discusses the methodology that will be used to deploy the yoga pose estimation on an android application, how the app is modeled and the working of each component is explained.