Difference: MagicWandOld (5 vs. 6)

Revision 62022-02-21 - UliRaich

Line: 1 to 1

META TOPICPARENT	name="TinyML"

The Magic Wand Example

Introduction

The magic wand example shows how to detect gestures using an accelerometer. Different types of accelerometers are easily available:

Changed:

<
<

The ADXL345 is a tree axis digital accelerometer by Analog Devices
The MPU6050 is a six axis device (Gyro and Accelerometer) from Ivensense. It is described by it datasheet and the register description.

>
>

The ADXL345 is a tree axis digital accelerometer by Analog Devices
I wrote a pure MircoPython driver for the ADXL345 available at https://github.com/uraich/IoT-Course/tree/master/exercises/solutions/exercise_16/adxl345.
The MPU6050 is a six axis device (Gyro and Accelerometer) from Ivensense. It is described by its datasheet and the register description document.
Jeff Rowberg has written a very complete MPU6050 driver for the Arduino in C++, which includes access to its Digital Motion Processor, whose description cannot be found anywhere on the WEB. I ported this driver to MicroPython together with a few example programs drafted after Jeff's C++ examples: https://github.com/uraich/IoT-Course/tree/master/exercises/solutions/exercise_16/mpu6050.

.

The LIS2dH MEMS digital output motion sensor from ST Microelectronics is an ultra low power high performance 3 axis accelerometer.

Line: 34 to 34

Providing a training data set

Changed:

<
<

In order to provide a training data set we must be able to record gestures. Therefore a driver for the accelerometer is needed as well as a program that recognizes movement and writes the accelerometer data on a file.

>
>

In order to provide a training data set we must be able to record gestures. We must therefore provide a program that recognizes the start and the end of a gesture (movement and inactivity detection) and which records the accelerometer data of the gesture onto a file. Gesture detection is of course also needed to be able to feed the accelerometer data into the trained model, which will then recognize the gesture.

Uli Raich - 2022-02-02

View topic | History: r12 < r11 < r10 < r9 | More topic actions...