Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
13 views1 page

Project Proposal

Uploaded by

xinyaofeng2026
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
13 views1 page

Project Proposal

Uploaded by

xinyaofeng2026
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Excercise Pose Classification

and Counting
project summary
This project aims to develop an intelligent fitness assistant capable of
classifying exercise poses such as squats, hip thrusts, push-ups, and lifts.
After accurately identifying each pose, the system will analyze the quality
of the user’s form, providing real-time feedback on technique. Additionally,
it will track and count the number of repetitions completed in each set,
offering users a comprehensive tool to enhance their workout experience.

technical analysis
Excercise pose classification

use CNN or KNN combined with LSTM or Transformer models to


classify excercise poses from video data. The video should be
analyzied and extracted some features related to human’s gesture.

Counting

For repetitive excercise, the system should accurately count the number
accomplished every set(maybe use time-series model to detect
periodic actions).

Pose Quality Analysis

Pose estimation algorithms (OpenPose or MediaPipe) might be used to


extract keypoint coordinates from the user’s body

Excercise Pose Classification and Counting 1

You might also like