INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
This application allows to train a person for various exercises and give live feedback on the screen with a beep sound. And
how it does that? the answer is that it detects the coordinates of the body joints using a wonderful machine learning algorithm called
MediaPipe. This algorithm is created and maintained by Google; it detects total 33 landmark on human body from head to toe. This
application then takes the coordinates and evaluates the vector geometry of the pose through the exercises, giving the user helpful
feedback in real-time. This allows the user to identify any potential problems with their pose and to quickly make adjustments to ensure
the accuracy of their form. The feedback provided by this application helps the user to improve their technique and to avoid any potential
injuries that could be caused by incorrect form. By evaluating the vector geometry of the pose, the application is able to provide valuable
insights that can be used to help the user achieve their fitness goals. Pose estimation is a type of method in which spatial locations or
parts of key body joints is calculated using the live camera of the device with a good camera quality so that all the body joints are visible
clearly. This computer vision technique is very uniquely detecting human body posture in live picture form and shows the keypoints of
the body like elbow, hip, knee as output to the device in live time which is a lot better than uploading image or video.
The output created by the algorithm is create by comparing the difference between the user joints angle input and the fixed angle saved
in the database.
Keywords:
CNN, MediaPipe, OpenCV, Numpy, Panda
Cite Article:
"Sports Training Action Detection", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 5, page no.i37-i48, May-2023, Available :http://www.ijnrd.org/papers/IJNRD2305806.pdf
Downloads:
000118761
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn