quotation:		[Copy]
		[Copy]

This Paper:Browse 2812 Download 48
一种基于连续波雷达的手势识别方法
孙延鹏,艾俊,屈乐乐
0 Fontlarge +\|Default\|Small
(沈阳航空航天大学电子信息工程学院，沈阳 110136)

摘要:

为了解决依靠光学传感器进行手势识别对外部环境依赖较大的问题，提出了一种基于连续波（Continuous Wave，CW）雷达的手势识别方法，并建立了4种手势动作的回波数据库。首先，对CW雷达回波进行短时傅里叶变换（ShortTime Fourier Transform，STFT）获取手势动作的时频谱；然后，通过设立阈值将时频谱中的背景杂波去除；接下来，对处理后的时频谱提取方向梯度直方图（Histogram of Oriented Gradient，HOG）特征；最后，采用支持向量机(Support Vector Machine，SVM)作为分类器，以HOG特征作为输入进行手势识别。实验结果表明，所提方法在普通室内环境下的识别精度超过95〖WT《Times New Roman》〗%〖WTBZ〗，能够对典型的手势动作进行有效识别。

关键词: 手势识别连续波雷达短时傅里叶变换方向梯度直方图支持向量机

DOI：

基金项目:

A hand gesture recognition method based on continuous wave radar

SUN Yanpeng,AI Jun,QU Lele

(College of Electronics Information Engineering，Shenyang Aerospace University，Shenyang 110136，China)

Abstract:

To solve the problem that external environment affects recognition accurary,a new hand gesture recognition method based on continuous wave(CW) radar is investigated,and a dataset of four typical hand gestures echo wave is generated.Firstly,the shorttime Fourier transform(STFT) of CW radar echoes from hand gestures is applied to produce the timefrequency spectrograms of hand gestures.Next,the background clutter in the timefrequency spectrograms is removed by setting up thresholds.Then,the histogram of oriented gradient(HOG) feature is extracted from the processed timefrequency spectrograms.Finally,the support vector machine(SVM) is used as a classifier and the HOG features are used as input for gesture recognition.The experimental results show that the recognition accuracy of the proposed method reaches more than 95〖WT《Times New Roman》〗%〖WTBZ〗 in a normal indoor environment,and it can effectively recognize typical hand gestures.

Key words: hand gesture recognition continuous wave radar short time Fourier transform histogram of oriented gradient support vector machine