Indoor human body posture recognition method based on millimeter wave radar

The invention discloses an indoor human body posture recognition method based on a millimeter-wave radar, relates to the technical field of millimeter-wave radars, and aims to solve the problem of low human body posture recognition accuracy in the prior art. A time-frequency graph and a time-distance graph are obtained by performing preprocessing and two-dimensional Fourier transform on original data, a neural network is established according to the characteristics of a generated human body posture data set, and a final recognition result is output in a decision-level fusion mode. According to the method provided by the invention, the collected indoor human body posture can be effectively recognized, and the recognition accuracy reaches 93.00%. 基于毫米波雷达的室内人体姿态识别方法，涉及毫米波雷达技术领域，针对现有技术中人体姿态识别准确率低的问题，本申请采用毫米波雷达采集了常见的室内人体姿态数据，通过对原始数据进行预处理和二维傅里叶变换的方式获得了时频图和时间距离图，根据生成的人体姿态数据集的特点搭建了神经网络，通过决策级融合的方式输出最后的识别结果。本申请的方法可以有效的识别出采集到的室内人体姿态，识别准确率达到了93.00％。