Adaptive Trajectories’ Constant False Alarm Rate Mirror Filters and Elevation Angle Evaluation for Multiple-Input Multiple-Output Radar-Based Hand Gesture Recognition

Tzu-Jung Tseng,Jian-Jiun Ding

Electronics(2024)

引用 0|浏览0
暂无评分
摘要
Gesture recognition technology has been quickly developed in the field of human–computer interaction. The multiple-input multiple-output (MIMO) radar is popular in gesture recognition because of its notable spatial resolution. This work proposes a MIMO radar-based hand gesture recognition algorithm with low complexity. We leverage low-complexity adaptive signal processing to extract trajectory information and minimize noise to create a system that can be applied in real-world applications with small training datasets. First, a spectrum analysis is utilized on range-Doppler maps (RDMs), and a cell-averaging constant false alarm rate (CA-CFAR) with mirror filters is applied to improve the robustness of noise. Then, the features related to the distance, speed, direction, and elevation angle of the moving object are determined using the proposed adaptive signal analysis techniques. For classification, the random forest algorithm is implemented. The proposed system can precisely distinguish and identify eight gestures, including waving, moving to the left or right, patting, pushing, pulling, and rotating clockwise or anti-clockwise, with an accuracy of 95%. Experiments demonstrate the capability of the proposed hand gesture recognition system to classify different movements precisely.
更多
查看译文
关键词
MIMO radar,hand gesture recognition,adaptive signal processing algorithm,random forest,mirror filtering,elevation angle estimation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要