Detecting the “let” in a table tennis game
Classification of the net vibrations with an accelerometer.
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
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.
100 % accuracy, 0.8 KB RAM, 0.2 KB Flash
3 classes:
95 % accuracy, 0.8 KB RAM, 0.5 KB Flash
A red point means we were incorrect.
Resources
Model created with NanoEdge AI Studio
A free AutoML software for adding AI to embedded projects, guiding users step by step to easily find the optimal AI model for their requirements.
Compatible with STM32
The STM32 family of 32-bit microcontrollers based on the Arm Cortex®-M processor is designed to offer new degrees of freedom to MCU users. It offers products combining very high performance, real-time capabilities, digital signal processing, low-power / low-voltage operation, and connectivity, while maintaining full integration and ease of development.
