keyboard_arrow_up
A Smart Fitness Action Correction and Exercise Assistance System based on Computer Vision and Artificial Intelligence

Authors

Jiarui Cai1 and Matthew Ngoi2, 1USA, 2California State Polytechnic University, USA

Abstract

Obesity and a lack of motivation for exercising is considered a major problem in the world because they lower the quality of life for many people. Mobile fitness applications are an emerging solution to this problem because of the unique features that are provided [12]. They are seen as a vital tool to motivate people suffering from obesity. Our solution uses a mobile application and machine learning to detect, track the movements of users in a video and give an analysis of the exercise. It is made up of three essential components: the mobile application which acts as a frontend, the online storage, and the server which hosts our AI model. The program was limited by the accuracy and effectiveness of the AI model. We aim to test the accuracy of the AI model by providing it with five videos with different amounts of repetitions for each of the sample exercises of pushup, pullup, squat, and plank for the experiment, which uses the calculation of the percent error [13]. We resulted in mostly excellent results with few inaccuracies, shown through the average percent error being 2.09%.

Keywords

Motivation, Mobile Applications, Machine Learning, AI Model.

Full Text  Volume 14, Number 5