MVJ College of Engineering Students Develop Self-Study Yoga Posture Assessment – India Education | Latest Education News | Global education news

Bangalore: Nowadays a lot of people practice yoga at home while watching TV / videos. However, without instructions from a trainer, a practitioner can perform incorrect poses and it can be difficult for beginners to identify it on their own. In this context, the students of the Computer Science and Engineering Department of the MVJ College of Engineering developed a method of Yoga Pose Tracking. Its goal is to estimate the human poses of multiple people in the videos and assign unique instance IDs for each key point across the frame. In a nutshell, the system evaluates a learner’s yoga position by identifying the pose by calculating the difference in body angles between a teacher’s position and that of a user, and displaying the wrong part between the pose. learner and instructor.

The students used Media Pipe Blaze Pose, which is a body pose tracking approach on the device. This is a convolutional neural network architecture for the evaluation of human posture that Google launched in August 2020. The network operates at over 30 frames per second and derives 33 2D body landmarks from a single image. Previous methods could only derive 17 benchmarks and relied heavily on sophisticated desktop environments. With CPU inference, Blaze Pose delivers real-time performance on mobile phones and delivers super real-time performance by taking advantage of GPU inference. Both heat maps and regression at key point coordinates are used in this method. Blaze Posture involves a two-stage detector-tracker ML pipeline for pose estimation. This pipeline initially locates the pose region of interest (ROI) inside the image using a detector. Then, the tracker predicts the 33 important points of the posture from this return on investment. The detector only runs on the first frame in video use cases and calculates the ROI for successive frames using key posture points from the previous frame.

Commenting on the project, Dr S. Anthoniraj, Associate Professor, Department of Computer Science and Engineering, MVJCE, said: “The yoga tracker has been amazing and has improved my yoga practice personally and would definitely be of benefit to people. . We must help people to recognize their capacities, to develop them and to express them in their own way. I appreciate the students who came up with this original idea and who put a lot of effort into creating this device.

Computer science and engineering students who worked on the project said: “It was a great opportunity to work together and develop the concept as our ambitious ideas became real and tangible and were within reach. It is a new approach to help individuals improve their lives and contribute to the development of a healthy community as a whole. In the future, we aspire to work on socially useful projects like this. The team of students involved in the project included Deepti Singh, Deepak Pandey, Hima VS and Bhaskar Katragadda.

Source link