Fitness Done Right: a Real-time Intelligent Personal Trainer for Exercise Correction

TL;DR

This paper introduces 'Fitness Done Right', a real-time AI system that detects exercise errors and provides correction advice to help users exercise correctly without professional trainers.

Contribution

It presents a novel multi-stage CNN-based system for real-time exercise pose detection and correction, specifically targeting plank and squat poses.

Findings

Error rate of 1.2% in pose detection

Effective real-time exercise correction system

Demonstrated system's practical usability

Abstract

Keeping fit has been increasingly important for people nowadays. However, people may not get expected exercise results without following professional guidance while hiring personal trainers is expensive. In this paper, an effective real-time system called Fitness Done Right (FDR) is proposed for helping people exercise correctly on their own. The system includes detecting human body parts, recognizing exercise pose and detecting errors for test poses as well as giving correction advice. Generally, two branch multi-stage CNN is used for training data sets in order to learn human body parts and associations. Then, considering two poses, which are plank and squat in our model, we design a detection algorithm, combining Euclidean and angle distances, to determine the pose in the image. Finally, key values for key features of the two poses are computed correspondingly in the pose error detection part, which helps give correction advice. We conduct our system in real-time situation with error rate down to $1.2\%$, and the screenshots of experimental results are also presented.