APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 4

A Lightweight Remote Gesture Recognition System with Body-motion Suppression and Foreground Segmentation Using FMCW Radar

Jingxuan Chen, University of Electronic Science and Technology of China, China, Yajie Wu, University of Electronic Science and Technology of China, China, Bo Zhang, University of Electronic Science and Technology of China, China, Shisheng Guo, University of Electronic Science and Technology of China, China, ssguo@uestc.edu.cn , Guolong Cui, University of Electronic Science and Technology of China, China
 
Suggested Citation
Jingxuan Chen, Yajie Wu, Bo Zhang, Shisheng Guo and Guolong Cui (2024), "A Lightweight Remote Gesture Recognition System with Body-motion Suppression and Foreground Segmentation Using FMCW Radar", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 4, e304. http://dx.doi.org/10.1561/116.00000061

Publication Date: 16 May 2024
© 2024 J.-X. Chen, Y.-J. Wu, B. Zhang, S.-S. Guo and G.-L. Cui
 
Subjects
 
Keywords
FMCW radarhand gesture recognitionmachine learninglightweight
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 333 times

In this article:
Introduction 
Methodology 
Experiment 
Conclusion 
References 

Abstract

In remote dynamic hand-gesture recognition, uncertainties in timing and distance of gesture occurrences, coupled with the subtle bodily perturbations induced by arm movements, pose substantial challenges to the accurate extraction of gesture features. In this paper, we propose a lightweight real-time gesture recognition system based on support vector machines. By analyzing the Doppler features of different motion states, a Doppler weighting factor was constructed to suppress bodily micro-motion interference in the range-time spectrum, and achieve foreground extraction of gesture signals concurrently. Furthermore, prior to the extraction of HOG features, we employ Gaussian filtering to suppress abrupt transitions and noise inherent in the gesture signals. This preprocessing significantly enhances the stability of feature extraction. Subsequently, the extracted features are input into an SVM for training and classification. Experimental results demonstrate that, for five distinct gestures exhibited in two different states –– standing and seated –– within a range of 1 to 5 meters, the recognition accuracy reaches 96%. This proves the feasibility of the proposed methodology, and its potential to realize real-time gesture recognition.

DOI:10.1561/116.00000061

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Emerging Wireless Sensing Technologies for Smart Environments
See the other articles that are part of this special issue.