Landing Page

Personal-Gym-Trainer

This is Team Luna Project repo for Cognition Hackathon

Description

The main objective of this research/project was to illustrate the potential of artificial intelligence (AI) techniques in sports on the example of weight training and exercising. Our research was focused on the implementation of pattern recognition methods for the evaluation of exercises performed by people with or without equipment. Over the last 1 to 2 years everyone has been confined to their homes without much physical activity. Hence, a personalized fitness trainer has the potential to replace a human trainer whenever possible. It can help various individuals to carry out routine exercises from the comfort of their homes without physically going to a gymnasium and performing the same. We have developed a personal Gym Trainer using Artificial Intelligence. This gym trainer works on a real-time basis and keeps track of the exercises performed, repetitions in each exercise and the number of sets performed as well. However, it will also work if one uploads an already recorded video, but in order to make things easier we have decided to keep the monitoring in real time.

Credentials for frontend login page

Username: admin Password: admin

Preview

Landing Page

https://github.com/Padm0069/Personal-Gym-Trainer/blob/main/Gym%20Trainer%20Landing.jpg

Hardware / Software Requirements

The hardware interface for the user would be any PC having a configuration of P-IV and above 2GB HDD for loading any OS so that it can interact with the system without any problem. The main interface would be monitor, keyboard and mouse.

Tech used

Skeleton modeling: This employs key points to depict the human body's skeletal system.
Contours modeling: This employs the body's raw breadth and extremities to display a person's figure's rectangular border boxes.
Modeling Volume: This analytical approach employs 3D body scans to capture the body using geometric meshes and forms.
Mediapipe - MediaPipe is a Framework for building machine learning pipelines for processing time-series data like video, audio, etc. This cross-platform Framework works in Desktop/Server, Android, iOS, and embedded devices like Raspberry Pi and Jetson Nano. Unlike power-hungry machine learning Frameworks, MediaPipe requires minimal resources. It is so tiny and efficient that even embedded IoT devices can run it. In 2019, MediaPipe opened up a whole new world of opportunity for researchers and developers following its public release. For further Understanding - https://learnopencv.com/introduction-to-mediapipe/
OpenCV