The feasibility of Q-band millimeter wave on hand-gesture recognition for indoor FTTR scenario

TL;DR

This paper investigates the use of Q-band millimeter wave technology for indoor hand-gesture recognition in FTTR scenarios, demonstrating a real-time system with promising generalization across users and environments.

Contribution

It introduces a real-time gesture recognition system using Q-band millimeter wave and CNN, addressing generalization issues across different scenarios and users.

Findings

Achieved generalized gesture recognition for 2 scenarios and 4 users.

Utilized spectrum features like micro-Doppler for gesture representation.

Validated the feasibility of Q-band millimeter wave in indoor gesture recognition.

Abstract

The generalization for different scenarios and dif-ferent users is an urgent problem for millimeter wave gesture recognition for indoor fiber-to-the-room (FTTR) scenario. In order to solve this problem and verify the feasibility of FTTR Q-band millimeter wave in gesture recognition, we build a real-time millimeter wave gesture recognition system. The moving hand-gestures are represented as a variety of time-variant spec-trum features, such as micro-Doppler feature, and then the feature learning and classification is realized by using a convo-lution neural network (CNN). The experimental results show that the millimeter wave gesture recognition system can achieve the generalized gesture recognition for 2 scenarios and 4 users.