augmented reality

Learn to Play like Minnesota Fats: Augmented Reality in the Pool Hall

Publication Type:

Report

Source:

ODCSSS (2009)

Keywords:

pool; sensors; augmented reality

Abstract:

Detecting human activities from sensors deployed in the environment is a difficult problem. Human activities are so varied that it is difficult to match sensed activities to observed actions. Instrumented homes have proved a popular platform for such sensors but experiences there show how challenging it can be. We believe that the pool hall is a more useful platform for the deployment of body-mounted sensor networks as the motions that can be captured correlate well to the activities that take place on the pool table. The problem is more narrow than detecting human activities in general. We will focus on a simple sensor, mounted on the cue, which is important as the cue is the sole actuator used to play the game. By correlating the force with which a player strikes the ball with their cue and the distance the ball travels we demonstrate that with a simple off-the-shelf sensor we can derive useful information. We conclude by describing a set of enhancements that enable a computer to “sense” the game of pool.

Learn to Play like Minnesota Fats - Augmented Reality in the Pool Hall - Deirdre Dalton

Deirdre Dalton prototyped a pool trainer as her ODCSSS project in summer of 2009 under the supervision of Lorcan Coyle. The aim of the project was to analyse the game of pool with the view to implementing some simple instructions to help tutor or teach a player.

A camera and sensor were used to take in information from the pool table. The camera was mounted directly above the pool table to capture ball colour and position. A SHIMMER, (Sensing Health with Intelligence, Modularity, Mobility, and Experimental Reusability) developed by Intel, was strapped to the base of the cue. Each SHIMMER contains a MicroSD - card slot, a rechargeable lithium-polymer battery, a 3-Axis accelerometer (1.5 6G) and a 3-Axis gyroscope (500 o/s). The accelerometer was of particular interest to this project as it was designed to react to very small changes in movement. It relayed the movements of the cue and was used to identify the strength of each shot.

A shot appeared as a large spike in the accelerometer data. The magnitude of this spike was calculated, and a strong correlation between the distance the ball travelled following this shot and the acceleration was determined. After much experimenting, a general equation was extracted which can determine how far the ball will travel, the moment it is struck by the cue.

Using this results it is possible to identify if a player is striking the ball with enough force to travel a certain distance, e.g., to pot a ball or roll up to a cushion for a safety shot. The work presented here is a strong starting point for future experimentation and analysis with a view to fully instrumenting a pool hall and providing teaching aids to a player to improve his/her game.

Further Information
There are more images from ODCSSS 2009 on Flickr. If you are interested in following up on this work or need further information contact Lorcan.

Syndicate content