Detecting the “let” in a table tennis game

Contact us

Did the ball hit the net? For all the ping pong games with no official referee, we developed a smart sensor that can detect when the ball hits the table or the net using machine learning! This application is easily transferable to other use cases using NanoEdge AI Studio.

Approach

– Use of an accelerometer to collect the vibration behavior of the net
– Define a collection of classes (3 classes of data: let, shock table, normal set)
– Log and import these data in the NEAI Studio tool and generate the corresponding library
– Test the library on the STEVAL-PROTEUS1 board

Sensor

Accelerometer: ISM330DHCX

Data

3 classes of data: Let, table choc, normal play
Length data: 64 * 3 axis
Data rate: 416 Hz; Range: 2g

Results

2 classes (let & normal play):
100 % accuracy, 0.8 KB RAM, 0.2 KB Flash
3 classes:
95 % accuracy, 0.8 KB RAM, 0.5 KB Flash

A green point means we are able to correctly predict if the finish will pass a visual inspection or not.
A red point means we were incorrect.