Skip to content

Commit 3ebfa36

Browse files
committed
Almost Finished
1 parent 247c3e2 commit 3ebfa36

File tree

2 files changed

+43
-19
lines changed

2 files changed

+43
-19
lines changed
71.5 KB
Loading

content/hardware/03.nano/boards/nano-matter/tutorials/08.ml-magic-wand/content.md

Lines changed: 43 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -28,23 +28,6 @@ This tutorial describes how to build a gesture recognition system based on a mac
2828

2929
The Arduino Nano Matter acts as a digital magic wand 🪄, where sensor data from its movements is processed by a model to classify and detect specific gestures. The inference results will tur
3030

31-
### How to Magic Wand Works?
32-
33-
In its **idle state**, the wand's LEDs remain **solid blue**, indicating that it is ready to detect a gesture.
34-
35-
When the wand is moved, the LEDs **turn off**, showing that gesture recognition has started.
36-
37-
Once the recognition process is complete:
38-
39-
If a gesture is successfully detected, the LEDs **blink rapidly for 4 seconds** in the color assigned to the recognized gesture:
40-
41-
- **Green** for "W" (wing gesture)
42-
- **Yellow** for "O" (ring gesture)
43-
44-
After this, the wand returns to its **idle state**, with the LEDs **solid blue** again.
45-
46-
***Gestures should be performed with wide and slow movements, lasting approximately 1-2 seconds for optimal recognition.***
47-
4831
### Goals
4932

5033
The goal of this project tutorial is to showcase the capabilities of the Arduino Nano Matter running Tiny Machine Learning models on the edge for gesture recognition. The wand can detect two gestures drawn in the air: **"W" (wing gesture)** and **"O" (ring gesture)**.
@@ -68,7 +51,6 @@ The goal of this project tutorial is to showcase the capabilities of the Arduino
6851
- [Modulino library](https://github.com/arduino-libraries/Modulino). This library adds the support for the Modulinos, you can install it from the **Library Manager** in the Arduino IDE.
6952
- [Silicon Labs core](https://github.com/SiliconLabs/arduino). This enables the Silicon Labs hardware including the Arduino Nano Matter support. You can install it from the **Boards Manager** in the Arduino IDE.
7053

71-
7254
### Download the Project Code
7355

7456
[![ ](assets/download.png)](assets/magic_wand_modulino.zip)
@@ -83,6 +65,28 @@ The **Silicon Labs** core contains the libraries and examples you need to work w
8365

8466
***The core version for this tutorial must be 2.3.0 or greater for the support of the Silabs Tensorflow Lite library.***
8567

68+
## How to Magic Wand Works?
69+
70+
In its **idle state**, the wand's LEDs remain **solid blue**, indicating that it is ready to detect a gesture.
71+
72+
When the wand is moved, the LEDs **turn off**, showing that gesture recognition has started.
73+
74+
Once the recognition process is complete:
75+
76+
If a gesture is successfully detected, the LEDs **blink rapidly for 4 seconds** in the color assigned to the recognized gesture:
77+
- **Green** for "W" (wing gesture)
78+
- **Yellow** for "O" (ring gesture)
79+
80+
![Recognizable Gestures](assets/gestures.png)
81+
82+
After this, the wand returns to its **idle state**, with the LEDs **solid blue** again.
83+
84+
***Gestures should be performed with wide and slow movements, lasting approximately 1-2 seconds for optimal recognition.***
85+
86+
### Data Collection
87+
88+
Accelerometer sensor readings are collected at a frequency of **104 Hz**, with a sample duration of approximately **2 seconds**. This results in **200** tuples of accelerometer (aX, aY, aZ) sensor data for each sample (`200 * 1/104 Hz = 1.92s`). Therefore, a total of **600 data points** are collected for each gesture (200 * 3 = 600).
89+
8690
## Project Setup
8791

8892
### Schematic Diagram
@@ -104,7 +108,7 @@ The Modulino are daisy-chained leveraging the Qwiic I2C connection with the Nano
104108

105109
You can mount the Nano Matter and the Modulinos on a custom 3D printed or laser cut base. Download the 3D files from [here](assets/3d-files.zip).
106110

107-
[3D Printed Base](assets/piece.PNG)
111+
![3D Printed Base](assets/piece.PNG)
108112

109113
### Programming
110114

@@ -630,5 +634,25 @@ In the Arduino IDE select the **Arduino Nano Matter** inside the _Silicon Labs_
630634

631635
![Nano Matter Sketch Upload](assets/code.png)
632636

637+
After the code is uploaded successfully, you can test your Nano Matter Magic Wand.
638+
639+
## Project Testing
640+
641+
Power the Nano Matter of your Magic Wand using a USB cable and start moving it following the Wing or Ring gesture to see if.
642+
643+
DEMO HERE
644+
645+
## Conclusion NEED UPDATE
646+
647+
In this tutorial you learned how to use the Nano Matter Display expansion kit, leveraging all its features like the E-ink screen to display high-contrast graphics with a low power consumption on 2.9" 384x168 resolution. Features like the built-in RGB LED, the 3-axis accelerometer and the temperature and humidity sensor were explained.
648+
649+
Thanks to the E-ink display, your IoT-oriented products can have a better and more natural user experience while maintaining a low power consumption. Allowing you to set up and commission your solution by scanning the QR code and showing real-time sensor data on the screen, being a game-changer feature for your IoT solutions.
650+
651+
### Next Steps
652+
653+
- Extend your knowledge with E-ink displays following the [Pervasive Displays documentation](https://docs.pervasivedisplays.com/).
654+
- Try all the examples included in the library for a deeper understanding on the API.
655+
- Start creating your own graphics to display custom data on the screen.
656+
633657

634658

0 commit comments

Comments
 (0)