The project focuses on analyzing cricket batting performance using computer vision and machine learning techniques. The system is designed to automatically classify five common cricket shots—cover drive, pull shot, cut shot, straight drive, and sweep shot—from video input. After identifying the shot type, the system predicts the outcome of the shot as either a six, four, catch, or drop ball. Using a combination of pose estimation, video processing, and machine learning models, the platform provides real-time feedback and analysis for players. The goal is to assist cricketers in improving their technique and understanding shot outcomes through AI-powered insights.
Tools: Python,Mediapipe,yolo v8,LSTM,opencv,tensorflow
Department: Department of Computer Science
Project Poster
