Efficient Convolutional Neural Network for FMCW Radar Based Hand Gesture Recognition
This work addresses gesture recognition for laptop users, offering a robust interface in varied conditions, but it is incremental as it applies an existing CNN method to new radar data.
The paper tackled hand gesture recognition using FMCW radar as a laptop interface by merging range, speed, and azimuth data into a single input for a convolutional neural network, achieving 96% accuracy on test sets and real-time performance.
FMCW radar could detect object's range, speed and Angleof-Arrival, advantages are robust to bad weather, good range resolution, and good speed resolution. In this paper, we consider the FMCW radar as a novel interacting interface on laptop. We merge sequences of object's range, speed, azimuth information into single input, then feed to a convolution neural network to learn spatial and temporal patterns. Our model achieved 96% accuracy on test set and real-time test.