Tesla-Rapture: A Lightweight Gesture Recognition System from mmWave Radar Point Clouds

TL;DR

Tesla-Rapture introduces a lightweight, accurate gesture recognition system using mmWave radar point clouds, enabling real-time performance on constrained devices like Raspberry Pi with significant improvements over existing methods.

Contribution

The paper develops Tesla, a novel MPNN graph convolution model for radar point clouds, achieving higher accuracy and faster prediction times than state-of-the-art methods, suitable for embedded systems.

Findings

Tesla outperforms existing models in accuracy.

Tesla predicts gestures nearly 8 times faster.

The system generalizes well across different scenarios.

Abstract

We present Tesla-Rapture, a gesture recognition interface for point clouds generated by mmWave Radars. State of the art gesture recognition models are either too resource consuming or not sufficiently accurate for integration into real-life scenarios using wearable or constrained equipment such as IoT devices (e.g. Raspberry PI), XR hardware (e.g. HoloLens), or smart-phones. To tackle this issue, we developed Tesla, a Message Passing Neural Network (MPNN) graph convolution approach for mmWave radar point clouds. The model outperforms the state of the art on two datasets in terms of accuracy while reducing the computational complexity and, hence, the execution time. In particular, the approach, is able to predict a gesture almost 8 times faster than the most accurate competitor. Our performance evaluation in different scenarios (environments, angles, distances) shows that Tesla generalizes well and improves the accuracy up to 20% in challenging scenarios like a through-wall setting and sensing at extreme angles. Utilizing Tesla, we develop Tesla-Rapture, a real-time implementation using a mmWave Radar on a Raspberry PI 4 and evaluate its accuracy and time-complexity. We also publish the source code, the trained models, and the implementation of the model for embedded devices.