Kishore D Mohan, Bindu S, Manjunath Nandi Krishnamurthy
Division of Yoga and Life Sciences, Swami Vivekananda Yoga Anusandhana Samsthana (S-VYASA), Bengaluru, Karnataka, India.
Department of Electronics and Communication Engineering, B N M Institute of Technology, Bengaluru, Karnataka, India.
Int J Yoga. 2022 Sep-Dec;15(3):254-261. doi: 10.4103/ijoy.ijoy_137_22. Epub 2023 Jan 16.
In recent days, is gaining more prominence and people all over the world have started to practice it. Performing with proper postures is beneficial. Hence, an instructor is required to monitor the correctness of postures. However, at times, it is difficult to have an instructor. This study aims to provide a system that will act as a personal instructor and practitioners can practice in their comfort zone. The device is interactive and provides audio guidance to perform different asanas. It makes the use of a camera to capture the picture of the person performing in a particular position. This captured pose is compared with the benchmark postures. A pretrained deep learning model is used for the classification of different postures using a standard dataset. Based on the comparison, the practitioner's posture will be corrected using a voice message to move the body parts in a certain direction. As the device performs all the operations in real-time, it has a quick response time of a few seconds. Currently, this work aids the practitioners in performing five Asanas, namely, /Half-moon pose, /Mountain pose, /Triangular pose, /Warrior pose, and /Tree pose.
近年来，[某项活动]越来越受到关注，全世界的人们都开始练习它。以正确的姿势进行[该项活动]是有益的。因此，需要一名教练来监督[该项活动]姿势的正确性。然而，有时很难有教练。本研究旨在提供一个系统，该系统将充当个人[该项活动]教练，练习者可以在自己的舒适区进行[该项活动]练习。该设备具有交互性，并提供音频指导以执行不同的[体式名称]。它利用摄像头捕捉处于特定姿势进行[该项活动]的人的图像。将捕捉到的姿势与基准姿势进行比较。使用预训练的深度学习模型，通过标准数据集对不同的[体式名称]姿势进行分类。基于比较结果，将使用语音消息纠正练习者的姿势，以使其身体部位向特定方向移动。由于该设备实时执行所有操作，其响应时间仅为几秒。目前，这项工作帮助练习者进行五种体式，即，半月式、山式、三角式、战士式和树式。
