计算机工程与应用2025，Vol.61Issue(11)：185-194,10.DOI:10.3778/j.issn.1002-8331.2402-0097
基于CWT和改进CBAM的手势识别方法
Gesture Recognition Method Based on Continuous Wavelet Transform and Improved CBAM
摘要
Abstract
Gesture,as an interaction mode with simple and intuitive movements and rich meanings,is widely used in vari-ous 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 resolu-tion and frequency resolution at the same time.To fully utilize the effective information,it is proposed to use the continu-ous 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%.关键词
手势识别/注意力机制/超宽带雷达/连续小波变换(CWT)Key words
gesture recognition/attention mechanism/ultra-wideband radar/continuous wavelet transform(CWT)分类
信息技术与安全科学引用本文复制引用
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):185-194,10.基金项目
2021年度中央引导地方科技发展资金(YDZJSX2021A007). （YDZJSX2021A007）
