Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Recognition of 'yoga-asana' using bidirectional LSTM with CNN features

Recognition of 'yoga-asana' using bidirectional LSTM with CNN features Recognising human activity in video is a highly challenging and complex task because a video contains lots of information along with complex variations. Yoga-asana recognition is one of the instances of human activity recognition that gained attention in last decade across the globe. In this paper, we developed an appearance-based recognition system for yoga-asana in video. The system has been implemented using end-to-end deep learning pipeline that includes convolutional neural network (CNN) and bidirectional long short-term memory (LSTM) network. Firstly, each video is down-sampled to 20 frames. Thereafter, spatial features are extracted from each frame and then in turn passed on to bidirectional LSTM for learning sequential information. Finally, Softmax classifier is applied on spatio-temporal representation of video for assigning one of the seven yoga-asana labels to it. For this study, we also created a customised dataset of seven yoga-asana (Bhujangasana, CatCow, Trikonasana, Vrikshasana, Padmasana, Shavasana, and Tadasana). The system achieved average test accuracy of 96.67% on customised dataset in 20-fold cross validation which is comparative to related work. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Arts and Technology Inderscience Publishers

Recognition of 'yoga-asana' using bidirectional LSTM with CNN features

Download PDF
13 pages

Loading next page...
 
/lp/inderscience-publishers/recognition-of-yoga-asana-using-bidirectional-lstm-with-cnn-features-ko00wFYDsA

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Inderscience Publishers
Copyright
Copyright © Inderscience Enterprises Ltd
ISSN
1754-8853
eISSN
1754-8861
DOI
10.1504/IJART.2021.120765
Publisher site
See Article on Publisher Site

Abstract

Recognising human activity in video is a highly challenging and complex task because a video contains lots of information along with complex variations. Yoga-asana recognition is one of the instances of human activity recognition that gained attention in last decade across the globe. In this paper, we developed an appearance-based recognition system for yoga-asana in video. The system has been implemented using end-to-end deep learning pipeline that includes convolutional neural network (CNN) and bidirectional long short-term memory (LSTM) network. Firstly, each video is down-sampled to 20 frames. Thereafter, spatial features are extracted from each frame and then in turn passed on to bidirectional LSTM for learning sequential information. Finally, Softmax classifier is applied on spatio-temporal representation of video for assigning one of the seven yoga-asana labels to it. For this study, we also created a customised dataset of seven yoga-asana (Bhujangasana, CatCow, Trikonasana, Vrikshasana, Padmasana, Shavasana, and Tadasana). The system achieved average test accuracy of 96.67% on customised dataset in 20-fold cross validation which is comparative to related work.

Journal

International Journal of Arts and Technology – Inderscience Publishers

Published: Jan 1, 2021

There are no references for this article.