Last weekend @devdevcharlie posted a gesture tracking machine learning demo to enhance the Street Fighter experience. The DIY version of the project starts by building a gesture tracking device using some simple hardware. Specifically, an Arduino MKR1000, a MPU6050 accelerometer/gyroscope and a button. Checkout the fritzing diagram below for the setup.
The tutorial uses the accelerometer to capture body movement for a training data set. Instead of tracking all movement, the button was used to start recording during relevant motion. Once gesture data for a punch, uppercut and hadoken were captured it was cleaned for use in a TensorFlow.js neural net classification model. The resulting model is able to distinguish between the three gestures (punch, uppercut, hadoken). The end result is a pretty impressive demo and a website that lets you test out your moves with a smartphone. If you’d like to try implementing the code yourself you can checkout @devdevcharlie’s tutorial or GitHub repo.
Stop breadboarding and soldering – start making immediately! Adafruit’s Circuit Playground is jam-packed with LEDs, sensors, buttons, alligator clip pads and more. Build projects with Circuit Playground in a few minutes with the drag-and-drop MakeCode programming site, learn computer science using the CS Discoveries class on code.org, jump into CircuitPython to learn Python and hardware together, TinyGO, or even use the Arduino IDE. Circuit Playground Express is the newest and best Circuit Playground board, with support for CircuitPython, MakeCode, and Arduino. It has a powerful processor, 10 NeoPixels, mini speaker, InfraRed receive and transmit, two buttons, a switch, 14 alligator clip pads, and lots of sensors: capacitive touch, IR proximity, temperature, light, motion and sound. A whole wide world of electronics and coding is waiting for you, and it fits in the palm of your hand.