Millimeter wave radar gesture recognition method and system based on cross-domain enhancement

Abstract

The invention discloses a millimeter wave radar gesture recognition method based on cross-domain enhancement. The method comprises the following steps: acquiring a millimeter wave radar gesture signal of a target human body; processing the millimeter wave radar gesture signal to obtain a dynamic distance angle diagram; using a data enhancement model to process the dynamic distance angle diagram to obtain a first dynamic distance angle diagram, the first dynamic distance angle diagram comprising a plurality of frame matrixes; processing the first dynamic distance angle diagram by using a gesture segmentation model to obtain a second dynamic distance angle diagram which represents a continuous DRAI frame sequence; and using a gesture recognition neural network model to process the second dynamic distance angle diagram to obtain a gesture recognition result, where the gesture recognition neural network model comprises a frame model and a sequence model. The invention further discloses a millimeter wave radar gesture recognition system based on cross-domain enhancement and electronic equipment.

Description

technical field [0001] The invention belongs to the field of signal processing, and in particular relates to a millimeter-wave radar gesture recognition method, system and electronic equipment based on cross-domain enhancement. Background technique [0002] Traditional gesture recognition is mainly divided into two types: gesture recognition based on wearable devices and gesture recognition based on computer vision. The former uses sensors worn by users to extract motion feature data to achieve gesture classification, but wearable devices are expensive and inconvenient to use, so they are difficult to promote. The latter uses RGB cameras or RGB-D cameras to collect gesture images or videos, and then uses image processing algorithms for recognition. But its main disadvantage is that the recognition accuracy is very dependent on light conditions, and the deployment of cameras may violate user privacy, thus limiting its application scenarios. [0003] Gesture recognition algo...

AI Technical Summary

Problems solved by technology

However, there are still two main problems in existing algorithms: (1) the robustness of the algorithm depends on large-scale training data, but collecting data is usually a time-consuming and laborious work; (2) in a certain domain (such as a specific After the model trained under the user, environment or location) is migrated to another new domain, the accuracy of the algorithm will be greatly reduced

This is because when different users and the same user perform gestures in different environments or in different positions, they will have different effects on the propagation of radar signals, resulting in differences in the motion features extracted for the same gesture.

Images