AI-Fitness-Tracker

We have build a AI based Fitness Tracker using OpenCV and Python. It can detect various body postures like bicep curls, squats and so on. We have used the pose estimation to find the correct points and using these points we'll get the desire angles. This tracker is going to track different fitness activities and render the results to the screen.

First we need to install and import all the necessary libraries such as numpy, mediapipe and opencv. Then starting with capturing video from webcam and setting up mediapipe instance.

Extracting the coordinates and joining them. Then it will find the angle between three defined coordinates.

At last we've applied the logic of curls counting, thereby by diplaying the counts on the screen.

So this is how it works. This AI based Fitness Tracker can guide an individual to maintain a good body posture. Thank for having us & providing this platform i.e. Hackathon Dotlash 5.O. We had a wonderful experience making this project and it was very helpful to enchance our skills.

AI-Fitness-Tracker - AI Fitness Tracker With Python

Related tags

Overview

AI-Fitness-Tracker

Owner

Sharvari Mangale

Transformer Huffman coding - Complete Huffman coding through transformer

Black-Box-Tuning - Black-Box Tuning for Language-Model-as-a-Service

This repository contains the code used for Predicting Patient Outcomes with Graph Representation Learning (https://arxiv.org/abs/2101.03940).

Codebase for "Revisiting spatio-temporal layouts for compositional action recognition" (Oral at BMVC 2021).

Official PyTorch Implementation of HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning (NeurIPS 2021 Spotlight)

A module that used for encrypt code which includes RSA and AES

Real life contra a deep learning project built using mediapipe and openc

TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network (SIGGRAPH 2020)

An example of semantic segmentation using tensorflow in eager execution.

Code of the paper "Multi-Task Meta-Learning Modification with Stochastic Approximation".

Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

KinectFusion implemented in Python with PyTorch

Human pose estimation from video plays a critical role in various applications such as quantifying physical exercises, sign language recognition, and full-body gesture control.

Nested cross-validation is necessary to avoid biased model performance in embedded feature selection in high-dimensional data with tiny sample sizes

A deep learning model for style-specific music generation.

This is the code for the paper "Motion-Focused Contrastive Learning of Video Representations" (ICCV'21).

Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations

Neurolab is a simple and powerful Neural Network Library for Python

A benchmark dataset for mesh multi-label-classification based on cube engravings introduced in MeshCNN

Personalized Transfer of User Preferences for Cross-domain Recommendation (PTUPCDR)