Skip to content

Smart web application using mediapipe, opencv, numpy and flask.

Notifications You must be signed in to change notification settings

jprokopski/DeepTraining

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

44 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

💪 Deep Training 💪


About

Deep Training is a web application that helps the user in home exercise. Application is using web camera to follow user movement during one of the eight exercises. On the screen, user can see the image from the camera with the circular markers located in the most important parts needed to do the picked exercise correctly. Application also shows exercise progress and simple interface with helpful command window and counter. This project was created as a part of the college course.

Getting Started

To run this application, you can either clone this repository or download the files using "download ZIP" button.

Prerequisites

To run this application, you need an environment with Python installed and a web browser (PC only).

Starting

  1. Enter run flask in the terminal.
  2. Copy shown address or click the link in the terminal.
  3. Pick one of the exercises in the main menu.

Note: be sure to have sufficient lighting in your room, so web camera can separate the body from the background

How It's Made:

Tech used: Python, HTML/CSS, MediaPipe, OpenCV, NumPy, Flask

Application is calculating angles between two important points on the body to check if the exercise was done correctly. It also uses a simple to understand *red/yellow/green* palette of colours to inform the user about exercise progress. After correct repetition of the exercise, application updates the counter. In the main menu exercises are marked with simple images with colour coded, interactive backgrounds. Skeleton with markers only shows body parts important for chosen exercise.

Authors

About

Smart web application using mediapipe, opencv, numpy and flask.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published