Hand Gesture Recognition from Doppler Radar Signals Using Echo State Networks

• URL: http://arxiv.org/abs/2602.04436v1
• Date: Wed, 04 Feb 2026 11:11:05 GMT
• Title: Hand Gesture Recognition from Doppler Radar Signals Using Echo State Networks
• Authors: Towa Sano, Gouhei Tanaka,
• Abstract summary: Hand gesture recognition (HGR) is a fundamental technology in human computer interaction (HCI)<n>In particular, HGR based on Doppler radar signals is suited for in-vehicle interfaces and robotic systems.<n>We propose an Echo State Network (ESN) approach for radar-based HGR, using frequency-modulated-continuous-wave (FMCW) radar signals.
• Score: 0.5745796568988237
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Spatiotemporal Radar Gesture Recognition with Hybrid Spiking Neural Networks: Balancing Accuracy and Efficiency [3.6205625120193354]
  We present the first use of Spiking Neural Networks (SNNs) for radar-based Human Activity Recognition (HAR)<n>Our novel hybrid architecture combines convolutional modules for spatial feature extraction with Leaky Integrate-and-Fire neurons for temporal processing.<n>We demonstrate the trade-offs of spiking computation in terms of accuracy, latency, memory, and energy, establishing SNNs as an efficient and competitive solution for radar-based HAR.
  arXiv  Detail & Related papers  (2025-09-27T13:31:11Z)
• Live Demonstration: Neuromorphic Radar for Gesture Recognition [11.7558457204162]
  We present a neuromorphic radar framework for real-time, low-power hand gesture recognition (HGR) using an event-driven architecture inspired by biological sensing.<n>Our system comprises a 24 GHz Doppler radar front-end and a custom neuromorphic sampler that converts intermediate-frequency (IF) signals into sparse spike-based representations.
  arXiv  Detail & Related papers  (2025-08-05T11:06:22Z)
• Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons [69.73249913506042]
  This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons to process time-domain signals directly.<n>By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity.<n> Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs.
  arXiv  Detail & Related papers  (2025-06-24T21:14:59Z)
• Advancing RFI-Detection in Radio Astronomy with Liquid State Machines [25.08630315149258]
  Radio Frequency Interference (RFI) from anthropogenic radio sources poses significant challenges to current and future radio telescopes.<n>In this work, we apply Liquid State Machines (LSMs), a class of spiking networks, to RFI-detection.<n>We train LSMs on simulated data derived from the Hyrogen Epoch of Reionization Array (HERA), a known benchmark for RFI-detection.<n>Our model achieves a per-pixel accuracy of 98% and an F1-Integrate of 0.743, demonstrating competitive performance on this highly challenging task.
  arXiv  Detail & Related papers  (2025-04-14T01:51:01Z)
• Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
  This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
  arXiv  Detail & Related papers  (2024-03-12T01:28:00Z)
• Deep Homography Estimation for Visual Place Recognition [49.235432979736395]
  We propose a transformer-based deep homography estimation (DHE) network. It takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Experiments on benchmark datasets show that our method can outperform several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-25T13:22:17Z)
• Fast and Accurate Cooperative Radio Map Estimation Enabled by GAN [63.90647197249949]
  In the 6G era, real-time radio resource monitoring and management are urged to support diverse wireless-empowered applications. In this paper, we present a cooperative radio map estimation approach enabled by the generative adversarial network (GAN)
  arXiv  Detail & Related papers  (2024-02-05T05:01:28Z)
• Semantic Segmentation of Radar Detections using Convolutions on Point Clouds [59.45414406974091]
  We introduce a deep-learning based method to convolve radar detections into point clouds. We adapt this algorithm to radar-specific properties through distance-dependent clustering and pre-processing of input point clouds. Our network outperforms state-of-the-art approaches that are based on PointNet++ on the task of semantic segmentation of radar point clouds.
  arXiv  Detail & Related papers  (2023-05-22T07:09:35Z)
• HDNet: Hierarchical Dynamic Network for Gait Recognition using Millimeter-Wave Radar [13.19744551082316]
  We propose a Hierarchical Dynamic Network (HDNet) for gait recognition using mmWave radar. To prove the superiority of our methods, we perform extensive experiments on two public mmWave radar-based gait recognition datasets.
  arXiv  Detail & Related papers  (2022-11-01T07:34:22Z)
• Three-Way Deep Neural Network for Radio Frequency Map Generation and Source Localization [67.93423427193055]
  Monitoring wireless spectrum over spatial, temporal, and frequency domains will become a critical feature in beyond-5G and 6G communication technologies. In this paper, we present a Generative Adversarial Network (GAN) machine learning model to interpolate irregularly distributed measurements across the spatial domain.
  arXiv  Detail & Related papers  (2021-11-23T22:25:10Z)
• Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model [20.670058030653458]
  Human motion recognition (HMR) based on wireless sensing is a low-cost technique for scene understanding. Current HMR systems adopt support vector machines (SVMs) and convolutional neural networks (CNNs) to classify radar signals. This paper proposes a deep spectrogram network (DSN) by leveraging the residual mapping technique to enhance the HMR performance.
  arXiv  Detail & Related papers  (2021-04-21T06:33:01Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.