Issuu

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 12 Issue: 11 | Nov 2025

p-ISSN: 2395-0072

www.irjet.net

AI-Based Posture Correction Systems in Fitness: A Literature Review DEEPAK E V Msc. Computer Science St.Thomas College (Autonomous) Thrissur ,680001 ,Kerala, India ---------------------------------------------------------------------***--------------------------------------------------------------------analysis of the current academic landscape concerning AIAbstract- This literature review comprehensively analyzes

based posture correction in fitness and gym environments. It will delineate the core concepts, categorize prevalent thematic applications, compare diverse methodologies, and identify prospective research avenues. The subsequent sections will detail the evolution and definitions of key concepts, classify existing research into thematic categories, and critically assess the underlying algorithms and hardware integrations.

recent advancements in AI-based posture correction systems for fitness and gym environments. The primary objective is to evaluate how artificial intelligence, particularly computer vision and pose estimation techniques, are revolutionizing personalized workout experiences. Key themes explored include the utilization of frameworks like OpenCV, MediaPipe, and YOLOv7-pose for real-time keypoint detection and joint angle calculation. The review highlights the crucial role of immediate, actionable feedback mechanisms—both visual and auditory—in enhancing exercise form, preventing injuries, and improving workout efficiency for users of all skill levels. Furthermore, it discusses system architecture, evaluation metrics, and challenges such as accuracy, latency, and adaptability. The synthesis demonstrates that these AI-driven solutions offer a scalable and accessible alternative to traditional human trainers, with significant potential for future integration with wearable devices, AR/VR platforms, and specialized rehabilitation applications.

2. LITERATURE SURVEY A. Evolution & Definitions The evolution of AI-driven fitness tracking systems marks a significant departure from traditional gym environments, which predominantly relied on human trainers for form correction and feedback. The burgeoning integration of artificial intelligence (AI) and computer vision has catalyzed the development of innovative solutions for personalizing and enhancing workout experiences. This progression has been supported by advancements in neural networks, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), and the introduction of multimodal datasets specifically for workout activities. Researchershavealsofocusedonoptimizing algorithms and developing lightweight models to improve the efficiency of human poseestimation techniques. Foundational concepts central to these systems include:

Key Words: Artificial Intelligence, Posture Correction, Computer Vision, Pose Estimation, OpenCV, MediaPipe, YOLOv7-pose, Real-time Feedback, Joint Angle Detection, Exercise Form Analysis, Injury Prevention, Fitness Technology, AI in Gym, Visual Feedback, Auditory Feedback, System Architecture, Latency, Accuracy, Adaptive Systems, Wearable Integration, AR/VR Fitness, Rehabilitation Systems.

• Pose Estimation: This is the process of identifying and tracking key points of the human body, such as joints and limbs, typically in real-time. Systems can detect either 17 key points, as seen in YOLOv7 and OpenPose, or 33 key points, as offered by MediaPipe.

1.INTRODUCTION The integration of artificial intelligence (AI) and computer vision in the fitness domain has garnered substantial attention, fundamentally transforming and enhancing workout experiences. Traditional fitness environments typically rely on human trainers for personalized feedback on exercise form and posture. However, the emergence of AIdriven solutions, particularly in pose estimation, presents an innovative alternative for real-time workout monitoring and correction. This technological shift is especially significant given the challenges individuals face, such as limited access to gyms, physical disabilities, social anxiety, or financial burdens associated with personal trainers. Maintaining correct posture during physical activity is paramount not only for maximizing workout benefits but also for reducing the risk of injuries like back pain or muscle strain. AI-powered systems can fill the void of personalized guidance, offering immediate, data-driven insights to improve user technique and ensure safer, more efficient training. This review aims to provide a comprehensive

Impact Factor value: 8.315

• Keypoint Detection: This refers to the application of computer vision techniques to precisely identify these specific anatomical points on the body. • Joint Tracking and Angle Calculation: Following keypoint detection, systems monitor joint movements and calculate angles between various body parts during exercises. These calculated angles are then compared against predefined ideal exercise models or thresholds to detect misalignments or errors in form. • Real-time Feedback: A critical component, this involves providing immediate corrective guidance to the user. This feedback can be visual, such as on-screen cues, or auditory, utilizing text-to-speech APIs.

ISO 9001:2008 Certified Journal

Page 425