Yoga tutor visualization and analysis using SURF algorithm

Patil, Siddharth; Pawar, A. B.; Peshave, Aditya; Ansari, Aamir N.; Navada, Arundhati

doi:10.1109/icsgrc.2011.5991827

Cited by 48 publications

(25 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section provides a brief review of related computer vision-based research works with a focus on (i) yoga pose classification [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ] and (ii) yoga pose grading [ 29 , 30 , 31 , 32 ], as summarized in Table 1 .…”

Section: Related Workmentioning

confidence: 99%

“…Despite the fairly popular studies on yoga pose classification, there are not many works on yoga pose grading. Patil et al proposed to identify yoga pose variations between different persons by comparing the similarity between the speeded up robust feature (SURF) extracted from the input pose images [ 29 ]. Chen et al proposed to capture the user body map, and then apply the skeleton to extract the human body feature points to identify the correct pose [ 30 ].…”

Section: Related Workmentioning

confidence: 99%

“…Despite the fairly popular studies in yoga pose classification, there is a lack in yoga pose grading research, except the works in [ 29 , 30 , 31 , 32 ]. The limitations of existing works lie in two aspects: First, it is a challenge to rely on the whole pose image for pose grading due to the fundamental difference between the learner’s pose image and the standard pose image.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A Computer Vision-Based Yoga Pose Grading Approach Using Contrastive Skeleton Feature Representations

Lin

Yang

et al. 2021

Healthcare

View full text Add to dashboard Cite

The main objective of yoga pose grading is to assess the input yoga pose and compare it to a standard pose in order to provide a quantitative evaluation as a grade. In this paper, a computer vision-based yoga pose grading approach is proposed using contrastive skeleton feature representations. First, the proposed approach extracts human body skeleton keypoints from the input yoga pose image and then feeds their coordinates into a pose feature encoder, which is trained using contrastive triplet examples; finally, a comparison of similar encoded pose features is made. Furthermore, to tackle the inherent challenge of composing contrastive examples in pose feature encoding, this paper proposes a new strategy to use both a coarse triplet example—comprised of an anchor, a positive example from the same category, and a negative example from a different category, and a fine triplet example—comprised of an anchor, a positive example, and a negative example from the same category with different pose qualities. Extensive experiments are conducted using two benchmark datasets to demonstrate the superior performance of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Computer Vision-Based Yoga Pose Grading Approach Using Contrastive Skeleton Feature Representations

Lin

Yang

et al. 2021

Healthcare

View full text Add to dashboard Cite

show abstract

“…The practice became more popular in western culture during the 1800s in Europe and eventually America. [1] As yoga became popular among academics its uses modernized and it has become popular among medical researchers due to its ability to cure diseases and improve a patient's health without the use of drugs [2]. Most recently, with the spread of Covid-19, yoga has become part of life to improve mental health and well-being and is able to resolve the issues caused by isolation and separation.…”

Section: Introductionmentioning

confidence: 99%

Yoga Pose Perfection using Deep Learning

Goyal¹,

Jain

2021

J Stud Res

View full text Add to dashboard Cite

Abstract Even with lots of attention and work in the computer vision and artificial intelligence field, human body pose detection is still a daunting task. The application of human pose detection is wide-ranging from health monitoring to public security. This paper focuses on the application in yoga, an art that has been performed for over a millennium. In modern society yoga has become a common method of exercise and there-in arises a demand for instructions on how to do yoga properly. Doing certain yoga postures improperly may lead to injuries and fatigue and hence the presence of a trainer becomes important. As many people don’t have the resources to have a yoga instructor or guide, artificial intelligence can act as a substitute and advise people on their poses. Currently, the research surrounding pose estimation for yoga mainly discusses the classification of yogic poses. In this work, we propose a method, using the Tensorflow MoveNet Thunder model, that allows real-time pose estimation to detect the error in a person's pose, thereby allowing them to correct it.

show abstract

“…Thus this phase is the heart of the research! 1.8 Scaling the model: Using the 'SURF Algorithm implementation [9] ' this imaginary character can resized according to the height and weight of the native user. Skinning is the process of attaching the 3D model (skin) to the rigged skeleton so that the 3D model can be manipulated by the controls of the rig.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Stretching Fitness using Augmented Reality

Gadesha

Laktaria

Ghose

2019

IJSRSET

View full text Add to dashboard Cite

Fitness is not about being better then someone else, it’s about being better then you use to be. Everyone is looking for their fitness but it’s quite difficult to find out time to practice appropriate stretching exercise or Yoga. Most of the people are not aware about the method of performing this kind of exercise or Yoga, thus the practice done in an incorrect method may harm the body muscles and even causes the side effects such as major drop in body energy, insomnia, body aches and pains, joint problems, female miss the period cycle or face the irregular periods, poor mental health and many more according to the capacity of human body[5]. Obsession with fitness is connected to convenience and flexibility that has given birth to on-demand fitness or yoga classes. People are running on the thorns of the clock now days. Thus we need a ‘home tutor in pocket’ (a mobile application) which can teach the correct method of various stretching exercise and yoga asana at our convenience. This mobile application created with the help of augmented reality[3] made the fitness routines more affordable and accessible, helps us to set the realistic fitness goal, monitor our workout routines and importantly teaches us the correct method of performing various stretching exercise and yoga asana. This research paper portray the objective, conceptualize the exclusive character(who is performing various exercise and yoga asana) using Photoshop , creation of 3D model using Maya, methodology, SURF Algorithm implementation, character scaling according to the height, weight and age using Unity 3D with Augmented Reality[2], technical aspects as well as social aspects.

show abstract

Yoga tutor visualization and analysis using SURF algorithm

Cited by 48 publications

References 1 publication

A Computer Vision-Based Yoga Pose Grading Approach Using Contrastive Skeleton Feature Representations

A Computer Vision-Based Yoga Pose Grading Approach Using Contrastive Skeleton Feature Representations

Yoga Pose Perfection using Deep Learning

Estimation of Stretching Fitness using Augmented Reality

Contact Info

Product

Resources

About