基于CWT和改进CBAM的手势识别方法

doi:10.3778/j.issn.1002-8331.2402-0097

摘要/Abstract

摘要： 手势作为一种交互方式，其动作简单直观、含义丰富，被广泛应用在各个领域。目前基于雷达的手势识别方法，大多采用短时傅里叶变换处理雷达回波信息，然而短时傅里叶变换窗口固定，不能同时提高时间分辨率和频率分辨率，为充分利用有效信息，提出采用连续小波变换处理雷达回波信号以提高手势识别精度。针对目前手势识别网络较为复杂，且受注意力机制能增强卷积神经网络特征表达的启发，提出一种基于改进CBAM（convolutional block attention module）注意力机制的手势识别网络。实验捕获了9种手势动作，建立了微多普勒图像数据集，结果表明，该方法实现简单，参数较少，识别准确率达到96.3%。

关键词: 手势识别, 注意力机制, 超宽带雷达, 连续小波变换（CWT）

Abstract: Gesture, as an interaction mode with simple and intuitive movements and rich meanings, is widely used in various fields. Most of the current radar-based gesture recognition methods use the short-time Fourier transform to process the radar echo information. However, the short-time Fourier transform window is fixed, and it cannot improve the time resolution and frequency resolution at the same time. To fully utilize the effective information, it is proposed to use the continuous wavelet transform to process the radar echo signals in order to improve the accuracy of gesture recognition. Aiming at the complexity of the current gesture recognition network and inspired by the fact that the attention mechanism can enhance the feature expression of convolutional neural network, a gesture recognition network based on the improved CBAM (convolutional block attention module) attention mechanism is proposed. Nine gestures are captured and a micro-Doppler image dataset is established. The results show that the method is simple to implement, has fewer parameters, and achieves a recognition accuracy of 96.3%.

Key words: gesture recognition, attention mechanism, ultra-wideband radar, continuous wavelet transform（CWT）

王丽春, 张朝霞, 符文林, 陈帅, 陈泓扬. 基于CWT和改进CBAM的手势识别方法[J]. 计算机工程与应用, 2025, 61(11): 185-194.

WANG Lichun, ZHANG Zhaoxia, FU Wenlin, CHEN Shuai, CHEN Hongyang. Gesture Recognition Method Based on Continuous Wavelet Transform and Improved CBAM[J]. Computer Engineering and Applications, 2025, 61(11): 185-194.

参考文献

[1] RUSTAM H, MUNEEB M, ALSUHIBANY S, et al. Home automation-based health assessment along gesture recognition via inertial sensors[J]. Computers, Materials Continua, 2023, 75(1): 2331-2346.
[2] ZHAO N, YANG X D, ZHANG Z Y, et al. Circulating nurse assistant: non-contact body centric gesture recognition towards reducing latrogenic contamination[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 25(6): 2305-2316.
[3] SAWASDEE S, PUMRIN S. Elderly care notification system using hand posture recognition[C]//Proceedings of the 4th International Conference on Digital Information and Communication Technology and Its Applications, 2014: 304-309.
[4] YE Q, YANG L Q, XUE G T. Hand-free gesture recognition for vehicle infotainment system control[C]//Proceedings of the IEEE Vehicular Networking Conference, 2018: 1-2.
[5] ZHENG L Q, BAI J, ZHU X C, et al. Dynamic hand gesture recognition in in-vehicle environment based on FMCW radar and transformer[J]. Sensors, 2021, 21(19): 6368.
[6] PU Q, JIANG S, GOLLAKOTA S. Whole-home gesture recognition using wireless signals (demo)[J]. ACM SIGCOMM Computer Communication Review, 2013, 43(4): 485-486.
[7] HUANG X A, W Q, ZANG S Y, et al. Tracing the motion of finger joints for gesture recognition via sewing RGO-coated fibers onto a textile glove[J]. IEEE Sensors Journal, 2019, 19(20): 9504-9511.
[8] CHANG J, PHINYOMARK A, BATEMAN S, et al. Wearable EMG-based gesture recognition systems during activities of daily living: an exploratory study[C]//Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, 2020: 3448-3451.
[9] WANG L, XIONG Y J, WANG Z, et al. Temporal segment networks: towards good practices for deep action recognition[C]//Proceedings of the European Conference on Computer Vision, 2016: 20-36.
[10] CHOI J W, RYU S J, KIM J H. Short-range radar based real-time hand gesture recognition using LSTM encoder[J]. IEEE Access, 2019, 7: 33610-33618.
[11] YANG Y, LI J H, LI B C, et al. MDHandNet: a lightweight deep neural network for hand gesture/sign language recognition based on micro-doppler images[J]. World Wide Web, 2022, 25(5): 1951-1969.
[12] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[13] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409. 1556, 2014.
[14] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
[15] PARK J, WOO S, LEE J Y, et al. BAM: bottleneck attention module[J]. arXiv:1807.06514, 2018.
[16] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[J]. arXiv:1807.06521, 2018.
[17] FU J, LIU J, TIAN H J, et al. Dual attention network for scene segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 3141-3149.
[18] WANG Q L, WU B G, ZHU P F, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020: 11531-11539.
[19] WANG L L, CHEN X Y, WEI X, et al. Research on gesture recognition and classification based on attention mechanism[C]//Proceedings of the IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference, 2022: 1617-1621.
[20] DU C, ZHANG L, SUN X P, et al. Enhanced multi-channel feature synthesis for hand gesture recognition based on CNN with a channel and spatial attention mechanism[J]. IEEE Access, 2020, 8: 144610-144620.
[21] SONG Y Q, WU L W, ZHAO Y Q, et al. High-accuracy gesture recognition using Mm-Wave radar based on convolutional block attention module[C]//Proceedings of the IEEE International Conference on Image Processing, 2023: 1485-1489.
[22] LAURENS V D M, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(11): 2579-2605.
[23] PARK G, CHANDRASEGAR V K, KOH J. Accuracy enhancement of hand gesture recognition using CNN[J]. IEEE Access, 2023, 11: 26496-26501.