Nalin Marwah

Cricket Bowling Optimization

Started Aug. 30, 2024

Abstract or project description

Fast bowling in cricket is a biomechanical process involving multiple phases: Run-up, Jump, Ball Delivery, and Follow-through. My project's goal focused on the Jump and Ball Delivery phases using computer vision, ML-based pose estimation, and physics-based analysis to identify key differences between professional and novice bowlers, providing both visual feedback (annotated videos) and data-driven insights (statistical clustering).

After evaluating multiple models, I developed a program using the Python-based Mediapipe Pose Estimator library with 33 pose points. Among 34 biomechanical parameters, the study identified 17 key parameters affecting bowling performance, focusing on arm, leg, wrist, and foot positioning with wrist speed. The original dataset was created from 30 professional and 5 novice bowlers' (46 balls) mp4 videos.

The software reliably captured and annotated video of novice bowlers, overlaying body angles on video frames and maximum wrist speed for subjective analysis. Statistical clustering using Z-score normalization and K-Means with DTW revealed that novice bowlers formed distinct biomechanical clusters separate from professionals, highlighting inefficiencies in their technique. Novices in this study achieved 35-64% skill parity from professionals. The rate of change in the right leg, foot, and wrist didn't significantly impact the bowling action. Novice bowlers exhibited lower wrist speed and higher variability in joint angles, affecting ball velocity and inconsistent mechanics.

This study provided a data-driven approach to improving fast bowling techniques and demonstrates the potential of AI and biomechanics in sports performance enhancement. Future work will involve multi-person poses, supervised learning, 3D coordinates, cricket ball detection, and on-smartphones used for real-time AI coaching systems.