Nalin Marwah

Cricket Bowling Optimization

Started Aug. 30, 2024

Abstract or project description

Fast bowling in cricket is a biomechanical process that involves multiple phases : Run-up, Jump, Ball Delivery, and Follow-through. The goal of my project was to analyze 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 Me- diapipe Pose Estimator library with 33 pose points. Among 34 biomechanical parameters,

the study identified 17 key parameters that affect 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 the video of novice bowlers, overlaying body angles on video frames and maximum wrist speed for subjective analysis. Statistical

clustering with Dynamic Time Warping revealed that novice bowlers formed distinct biome- chanical clusters separate from professionals, highlighting inefficiencies in their technique.

Using Dynamic Time Warping, the data were able to be aligned despite the different time frames of the videos. The novices in this study achieved 35-64% skill parity with the professionals. The rate of change in the right leg, foot, and wrist did not significantly impact the bowling action. Novice bowlers exhibited lower wrist speed and greater variability in joint angles, affecting ball velocity and inconsistent mechanics.

This study employed a data-driven approach to enhance fast bowling techniques, demon- strating the potential of AI and biomechanics to improve sports performance. Future work

on this study will expand to incorporate a multi-person model, allowing for the analysis of a wider range of videos and enabling 3D pose estimation to enhance the accuracy of the angles. The addition of a supervised AI learning model and ball detection will enable real-life AI coaching and analysis, making it easier for fast bowlers to receive clear, actionable feedback and quantitative data. Making this into an app will allow for easy accessibility on even a phone, so bowlers can receive real-time AI coaching.