A Novel Robust Method for Hand Gesture Recognition Based on Millimeter-Wave Radar

Hongzhi Li; Lanyang Kang; Qinglong Hua; Bin Zhao

doi:10.1109/ICMMT65948.2025.11188695

A Novel Robust Method for Hand Gesture Recognition Based on Millimeter-Wave Radar

Hongzhi Li
, Lanyang Kang
, Qinglong Hua
, Bin Zhao^*

^*Corresponding author for this work

School of Electronics and Information Engineering, Harbin Institute of Technology
Henan Academy of Innovations in Medical Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

As one of the most commonly used communication methods, gestures have gradually become a research hotspot in human-computer interaction. To address the issue of target-like interference in millimeter-wave radar gesture recognition, this paper will employ the Cubature Kalman Filter (CKF) algorithm to process gesture data and compare the results with those obtained by the Unscented Kalman Filter (UKF) algorithm. To tackle the problems of low accuracy and poor robustness in gesture recognition using deep learning, this paper constructs a Dual-Stream Fusion Residual Network (DSFRN) by leveraging multi-feature domains after feature fusion for gesture data learning and recognition. Then we integrate the Convolutional Block Attention Module (CBAM) into the network. Experiments show that the recognition accuracy of fused features can reach 97.45%.

Original language	English
Title of host publication	2025 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Edition	2025
ISBN (Electronic)	9798331525736
DOIs	https://doi.org/10.1109/ICMMT65948.2025.11188695
State	Published - 2025
Externally published	Yes
Event	16th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025 - Xi�an, China Duration: 19 May 2025 → 22 May 2025

Conference

Conference	16th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025
Country/Territory	China
City	Xi�an
Period	19/05/25 → 22/05/25

Keywords

Gesture recognition
dual-channel network
millimeter wave radar
target-like interference suppression

Access to Document

10.1109/ICMMT65948.2025.11188695

Cite this

@inproceedings{29402b096a7a4c50a6e21e4af873e88f,

title = "A Novel Robust Method for Hand Gesture Recognition Based on Millimeter-Wave Radar",

abstract = "As one of the most commonly used communication methods, gestures have gradually become a research hotspot in human-computer interaction. To address the issue of target-like interference in millimeter-wave radar gesture recognition, this paper will employ the Cubature Kalman Filter (CKF) algorithm to process gesture data and compare the results with those obtained by the Unscented Kalman Filter (UKF) algorithm. To tackle the problems of low accuracy and poor robustness in gesture recognition using deep learning, this paper constructs a Dual-Stream Fusion Residual Network (DSFRN) by leveraging multi-feature domains after feature fusion for gesture data learning and recognition. Then we integrate the Convolutional Block Attention Module (CBAM) into the network. Experiments show that the recognition accuracy of fused features can reach 97.45\%.",

keywords = "Gesture recognition, dual-channel network, millimeter wave radar, target-like interference suppression",

author = "Hongzhi Li and Lanyang Kang and Qinglong Hua and Bin Zhao",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 16th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025 ; Conference date: 19-05-2025 Through 22-05-2025",

year = "2025",

doi = "10.1109/ICMMT65948.2025.11188695",

language = "英语",

booktitle = "2025 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "美国",

edition = "2025",

}

Li, H, Kang, L, Hua, Q & Zhao, B 2025, A Novel Robust Method for Hand Gesture Recognition Based on Millimeter-Wave Radar. in 2025 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025 - Proceedings. 2025 edn, Institute of Electrical and Electronics Engineers Inc., 16th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025, Xi�an, China, 19/05/25. https://doi.org/10.1109/ICMMT65948.2025.11188695

A Novel Robust Method for Hand Gesture Recognition Based on Millimeter-Wave Radar. / Li, Hongzhi; Kang, Lanyang; Hua, Qinglong et al.
2025 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025 - Proceedings. 2025. ed. Institute of Electrical and Electronics Engineers Inc., 2025.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Novel Robust Method for Hand Gesture Recognition Based on Millimeter-Wave Radar

AU - Li, Hongzhi

AU - Kang, Lanyang

AU - Hua, Qinglong

AU - Zhao, Bin

PY - 2025

Y1 - 2025

N2 - As one of the most commonly used communication methods, gestures have gradually become a research hotspot in human-computer interaction. To address the issue of target-like interference in millimeter-wave radar gesture recognition, this paper will employ the Cubature Kalman Filter (CKF) algorithm to process gesture data and compare the results with those obtained by the Unscented Kalman Filter (UKF) algorithm. To tackle the problems of low accuracy and poor robustness in gesture recognition using deep learning, this paper constructs a Dual-Stream Fusion Residual Network (DSFRN) by leveraging multi-feature domains after feature fusion for gesture data learning and recognition. Then we integrate the Convolutional Block Attention Module (CBAM) into the network. Experiments show that the recognition accuracy of fused features can reach 97.45%.

AB - As one of the most commonly used communication methods, gestures have gradually become a research hotspot in human-computer interaction. To address the issue of target-like interference in millimeter-wave radar gesture recognition, this paper will employ the Cubature Kalman Filter (CKF) algorithm to process gesture data and compare the results with those obtained by the Unscented Kalman Filter (UKF) algorithm. To tackle the problems of low accuracy and poor robustness in gesture recognition using deep learning, this paper constructs a Dual-Stream Fusion Residual Network (DSFRN) by leveraging multi-feature domains after feature fusion for gesture data learning and recognition. Then we integrate the Convolutional Block Attention Module (CBAM) into the network. Experiments show that the recognition accuracy of fused features can reach 97.45%.

KW - Gesture recognition

KW - dual-channel network

KW - millimeter wave radar

KW - target-like interference suppression

UR - https://www.scopus.com/pages/publications/105020819956

U2 - 10.1109/ICMMT65948.2025.11188695

DO - 10.1109/ICMMT65948.2025.11188695

M3 - 会议稿件

AN - SCOPUS:105020819956

BT - 2025 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2025

Y2 - 19 May 2025 through 22 May 2025

ER -

A Novel Robust Method for Hand Gesture Recognition Based on Millimeter-Wave Radar

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this