Micro Gesture Recognition of the Millimeter-Wave Radar Based on Multi-branch Residual Neural Network

A formal gesture recognition based on optics has limitations, but millimeter-wave (MMW) radar has shown significant advantages in gesture recognition. Therefore, the MMW radar has become the most promising human-computer interaction equipment, which can be used for human-computer interaction of vehicle personnel. This paper proposes a multi-branch network based on a residual neural network (ResNet) to solve the problems of insufficient feature extraction and fusion of the MMW radar and immense algorithm complexity. By constructing the gesture sample library of six gestures, the MMW radar signal is processed and coupled to establish the relationship between the motion parameters of the distance, speed, and angle of the gesture information and time, and the depth features are extracted. Then the three depth features are fused. Finally, the classification and recognition of MMW radar gesture signals are realized through the full connection layer. Through experiments, the accuracy of fusion gesture classification based on the multi-branch ResNet reached 97.2%. The results show that the proposed multi-branch ResNet has the advantages of the conventional ResNet, can accept multiple inputs, and has the benefits of high recognition accuracy.