Radar-simulation-image-based human body motion classification method of a convolution neural network

Abstract

The invention relates to a radar-simulation-image-based human body motion classification method of a convolution neural network. The method comprises: step one, establishing a time-frequency image data set containing a variety of human motions; step two, enhancing radar time-frequency image data; step three, establishing a convolution neural network model; to be specific, using a handwriting recognition network LeNet as a basis, introducing a modified linear unit ReLU to replace an original Sigmoid activation function as an activation function of the convolution network based on three convolution layers, two pool layers and two fully connection layers, adding a pool layer and reducing a fully connection layer to form a convolution neural network structure including three convolution layers, three pool layers and one fully connection layers, and adjusting an interlamination structure and an in-layer structure of the network and training parameters to realize a good classification effect; and training the convolution neural network model.

Description

technical field [0001] The invention belongs to the field of radar target classification and deep learning, and relates to the problem of using radar to classify human actions. Background technique [0002] In the process of interacting with the outside world, in addition to communicating through voice, people often use body language, that is, convey information through actions. Human action classification has a wide range of application scenarios in many fields, such as intelligent monitoring, human-computer interaction, virtual reality, somatosensory games, medical monitoring, etc. Most of the current research on human action recognition focuses on vision-based recognition. The core is to process and analyze the original image or image sequence data collected by the sensor through the computer, and learn and understand the human's actions and actions. However, conditions such as different lighting, viewing angles, and backgrounds will produce differences in poses and char...

AI Technical Summary

Problems solved by technology

However, conditions such as different lighting, viewing angles, and backgrounds can produce differences in poses and characteristics of the same human action.

In addition, there are still problems such as human body self-occlusion, partial occlusion, individual differences in human body, and multi-person recognition objects. These are the bottlenecks that the existing human motion classification schemes based on vision methods are difficult to break through.

Images