Ultra-wideband radar identity recognition method based on breathing sample space

Abstract

The invention discloses an ultra wideband radar identity recognition method based on a breathing sample space. The method comprises the steps that an ultra wide band radar sensor collects ultra wide band radar echo signals with human body breathing characteristics returned according to a transmission pulse of a fixed period; after phase noise correction and filtering preprocessing are carried out on the ultra-wideband radar echo signal, an energy characteristic peak detection algorithm is adopted to detect the preprocessed ultra-wideband radar echo signal so as to determine a distance unit where a target is located; the method also includes extracting a one-dimensional breathing time-domain signal of a distance unit where the target is located, filtering the one-dimensional breathing time-domain signal, and performing fast Fourier transform on the filtered breathing time-domain signal to extract a breathing frequency; dividing the preprocessed ultra-wideband radar echo signal according to the respiratory frequency to obtain a series of sub-matrixes as samples in a respiratory sample space; using a convolutional neural network and a sample for modeling a breathing sample space to obtain a target identity recognition result, so that identity recognition can be carried out on a target user according to breathing features.

Description

technical field [0001] The invention belongs to the field of identification, and in particular relates to an ultra-wideband radar identification method based on breath sample space. Background technique [0002] Ambient assisted living technology can provide intelligent life services for specific groups of people such as the elderly, and identity recognition is the basis for providing targeted services, and its research has received more and more attention. Among the existing methods, the active electronic tag method needs to wear a fixed object, which is intrusive and not easy to develop a wearing habit; the identification method of dynamically collecting face images and obtaining facial physiological characteristics through the camera can be used in home life. In the scene, this method has the risk of privacy leakage, and also has high requirements for lighting and shooting angles, and its use at night is limited; while other methods that obtain physiological characteristi...

AI Technical Summary

Problems solved by technology

The problem is that the above method relies on the invasive collection of physiological signals of the human body, that is, it needs to install corresponding sensors on the target body, which is quite inconvenient to use

The method of using wireless signals to collect respiratory characteristics is more practical. For example, the patent application with the publication number CN111723832A discloses a method of identification based on respiratory signs. The method uses WiFi devices to collect channel state information (CSI), and according to the phase information of CSI To estimate the vital sign signal, because the WiFi transmitter and receiver work independently, lack of coherence, its resolution and sensitivity are relatively limited, so it can only roughly characterize the respiratory signal

Images