DefinePK

Abstract

Recent advancements in posture estimation, action recognition, and motion prediction enable detailed analysis of motions, hence facilitating the identification of possible errors during exercise. This research examines the validity and performance evaluation of a method designed to recommend corrective indices or measurements for lower-body workouts, namely squats. This project involves the compilation of a dataset of films, as well as 2D and 3D representations of both right and wrong executions of various activities, namely squats, lunges, planks, and pickups. The study employs datasets from many squat types, including bodyweight squats, goblet squats, and pistol squats, among others. The suggested method examines motion patterns and detects deviations from the optimal performance of each squat variant using sophisticated motion detection algorithms and machine learning. The technique's efficacy is assessed by juxtaposing its remedial recommendations with expert human evaluations, yielding insights into its correctness, efficiency, and applicability. This research investigates the efficacy of corrective indicators to improve exercise performance, avert injuries, and facilitate successful training. The results highlighted the technique's effectiveness, with 97% of squats and 100% of planks being correctly classified post-correction, showcasing its capability to enhance performance and prevent injuries. The classification accuracy for squats and lunges was not perfect, with 60% accuracy for squats and 83% for lunges, indicating areas for further improvement.