Air Pencil

AIR PENCIL is a part of the TensorFlow Lite for Microcontroller Experiments Challenge, adding to a collection of open source, interactive projects designed to demonstrate some fun ways to combine Arduino and TensorFlow Lite for Microcontrollers.

These projects were built with the

• Arduino Sense 33 BLE
• TensorFlow Lite for Microcontrollers
• Standard web technologies ( HTML, CSS & Javascript ) and p5.js ✨

Other experiments to explore:

• Air Snare lets you play the drums in the air.
• Tiny Motion Trainer lets you train and test IMU based TFLite models in the browser.
• Morning Mountain lets you stop your alarm clock from ringing by striking a pose.
• Astrowand lets you draw shapes in the air to form constellations.
• Finger User Interface or FUI (pronounced Foo-ey) lets you control connected devices with the wave of a finger.

https://princep.github.io/Edu-Pencil/

Air pencil is built with Tiny Motion Trainer, it lets you train and test IMU based TFLite models in the browser.

• Get the kit.

• Setup the pencil

📷 📷

• Connect the Arduino Nano to micro-usb. It will start blinking.

Intiailize the parameters for the motion capture.

• Capturing threshold = 0.2
• Number of samples = 30
• Delay = 0.3
• Intiailize the parameters for the motion capture.Capturing threshold = 0.2Number of samples = 30Delay = 0.3
• Capture all the data with at least 20 samples.

Gesture / : A forward slant gesture training

Captured dataset

• Training and Testing

Train the model

Test using the same setup

Download the quantized model

• Download the quantized model

Replace the model and its parameters in sketch.js file.

• Replace the model and its parameters in sketch.js file.

Installation

Air Pencil requires Node.js v10+ to run. You need live-server-https, python2 or 3 installed

cd Edu-Pencil
npm install
sh serve.sh

Then go to https://localhost:8181 in your browser and follow instructions

License

MIT