A Survey on AI-Based Athlete Performance Analysis and Injury Detection
A Survey on AI-Based Athlete Performance Analysis and Injury Detection
Authors:
Sheba Jebakani1, Ameena Fathima2, C Sindhu3, Deeksha J4, Deepika K A5
Assistant Professor, Dept of Computer Science and Engineering, KSIT, Karnataka, India1 Student, Dept of Computer Science and Engineering, KSIT, Karnataka, India2-5
Abstract-This paper presents a comprehensive survey of artificial intelligence (AI) techniques used in athlete performance analysis and injury detection. In recent years, AI-based approaches, including machine learning, deep learning, computer vision, and pose estimation, have gained significant importance in sports analytics. These techniques enable the analysis of athlete movements, posture evaluation, motion pattern recognition, and overall performance enhancement. Pose estimation methods such as OpenPose and MediaPipe are widely used to detect human body keypoints from images and videos, allowing accurate assessment of body movements and exercise techniques. AI systems also evaluate critical performance parameters such as speed, strength, endurance, agility, and movement efficiency. Furthermore, AI-based injury detection systems identify abnormal movement patterns and improper posture that may lead to injuries. The integration of wearable sensors with AI models enables real-time monitoring of physiological parameters such as heart rate, fatigue, and muscle activity. This survey reviews commonly used AI techniques, existing methodologies, datasets, challenges, and recent advancements in sports analytics. It highlights the advantages and limitations of current approaches and emphasizes the potential of AI in enhancing athlete performance, optimizing training strategies, and reducing injury risks.
Keywords: Artificial Intelligence, Machine Learning, Pose Estimation, Athlete Performance Analysis, Injury Detection, Computer Vision.