Hand Gesture Recognition from Doppler Radar Signals Using Echo State Networks

2026-02-04

AI Summary

This work proposes a lightweight and efficient approach to address the high computational cost of conventional deep learning methods in Doppler radar-based gesture recognition. By transforming raw FMCW radar signals into range–time and Doppler–time feature maps, the method employs a novel multi-reservoir Echo State Network (ESN) architecture, followed by classification via ridge regression, support vector machines, or random forests. This design effectively integrates spatiotemporal and frequency-domain features, achieving superior recognition performance while substantially reducing computational overhead. Experimental results on the Soli (11-class) and Dop-NET (4-class) datasets demonstrate that the proposed method outperforms existing approaches, highlighting its excellent trade-off between accuracy and efficiency.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Hand gesture recognition (HGR) is a fundamental technology in human computer interaction (HCI).In particular, HGR based on Doppler radar signals is suited for in-vehicle interfaces and robotic systems, necessitating lightweight and computationally efficient recognition techniques. However, conventional deep learning-based methods still suffer from high computational costs. To address this issue, we propose an Echo State Network (ESN) approach for radar-based HGR, using frequency-modulated-continuous-wave (FMCW) radar signals. Raw radar data is first converted into feature maps, such as range-time and Doppler-time maps, which are then fed into one or more recurrent neural network-based reservoirs. The obtained reservoir states are processed by readout classifiers, including ridge regression, support vector machines, and random forests. Comparative experiments demonstrate that our method outperforms existing approaches on an 11-class HGR task using the Soli dataset and surpasses existing deep learning models on a 4-class HGR task using the Dop-NET dataset. The results indicate that parallel processing using multi-reservoir ESNs are effective for recognizing temporal patterns from the multiple different feature maps in the time-space and time-frequency domains. Our ESN approaches achieve high recognition performance with low computational cost in HGR, showing great potential for more advanced HCI technologies, especially in resource-constrained environments.

Problem

• Hand Gesture Recognition
• Doppler Radar
• Computational Efficiency
• Human-Computer Interaction
• Resource-Constrained Environments

Innovation

• Echo State Network
• Doppler radar
• Hand Gesture Recognition
• Multi-reservoir architecture
• Low-computational HCI