SHARP logo Hope College, Holland, Michigan
All About SHARP applicants

projects

program directors

 

 

All About Sharp
Project details

Automatic Point Detection in Recorded Tennis Matches

Project Full Title:

Automatic Point Detection in Recorded Tennis Matches

Project Mentor(s):

McFall,Ryan

Project Mentor(s) EMail:

mcfall@hope.edu

Project Start Date:

5/24/2021

Project End Date:

7/23/2021

Project Description:

This project will utilize machine learning, specifically convolutional neural networks (CNN), to help remove "dead time" from a record tennis match. Dead time is defined to be the time in between points. To accomplish this, we will need to (1) obtain footage of recorded tennis matches between different levels and ages of competitors; (2) identify the starting frames of each point; (3) train a CNN to recognize the starting frames; and (4) write code to process the video to remove the dead time. Identification of players, the ball, and other specific components of a tennis match will utilize the "You Only Look Once" (YOLO) object detection framework. If time permits, we will also seek to identify other sequences of interest within the point, such as specific types of shots (forehands, backhands, volleys, overheads, etc.) Programming for the project will take place in the Python programming language. While prior knowledge of Python will be helpful, it is not required. Preference will be given to students who have completed both CSCI 225 and CSCI 235 by the beginning of the project. Completion of CSCI 245 will be a bonus, but is not required. No background in machine learning is necessary. You also don't have to be a tennis player, but you will be expected to learn and understand tennis terminology.

External Link:

BACK

 

 

© 2007-2010 Hope College, Holland, Michigan, USA. All rights reserved.