Answers are grounded in this paper and cite their sources.
In recent years, the amalgamation of computer vision and deep learning technologies has led to the advancement of fitness and health‐related movement tracking in gyms. Such advancements have resulted in exercise‐related analyses within the gym environment. These analyses were made possible by collecting real‐time movement data from people working in the gym, such as kinematics, kinetics, EMG, and so forth. Further, real‐time feedback was provided using movement data to avoid injuries while working in the gym. The newly emerging field of movement tracking in the gym uses technologies that could improve workout accuracy and optimization in the fitness routine. Further, a broad spectrum of recent research assesses computer vision techniques and deep learning models to evaluate physical performance and create real‐time corrective feedback and monitoring systems. The review addresses innovative noncontact and contact‐based monitoring systems that could capture movement patterns and their specific datasets. Furthermore, the article highlights the challenges in real‐world gym settings, such as lighting variations, occlusion by gym equipment or people, and the high computational requirements of real‐time processing. The article also elaborates on different methods and models used for movement tracking in the gym and their advantages and disadvantages. Hence, such a review emphasizes the emergence of transformative computer vision and deep learning technology to revolutionize the fitness domain. This article is categorized under: Application Areas > Health Care Technologies > Artificial Intelligence Fundamental Concepts of Data and Knowledge > Human Centricity and User Interaction
No takes yet. Share an insight, caveat, or question.
A 2025 study studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: