Doppler radar provides high quality data of movements in the radar’s surrounding environment, including the movement’s direction and speed, even while the radar itself remains stationary. However, the resulting data is often difficult to decipher on it’s own. Using machine learning we can recognize patterns like hand gestures from the messy signals generated by the Doppler radar. With TinyML, developers can easily run radar gesture recognition models on embedded devices with Doppler radar sensors using minimal device resources.
This is a companion discussion topic for the original entry at https://www.edgeimpulse.com/blog/infineon-sense2gol-pulse