Radar human body motion state classification algorithm and system based on model fusion

Abstract

The invention belongs to the technical field of radars, and particularly relates to a radar human body motion state classification algorithm and system based on model fusion, and the method comprisesthe steps: obtaining a training set; constructing a support vector machine model according to the training set; obtaining a predicted value of the support vector machine model according to the supportvector machine model; and constructing an extreme gradient boosting tree model according to the prediction value of the support vector machine model. According to the method, a support vector machinemodel and an extreme gradient boosting tree model are fused through a staging model fusion method; the support vector machine model is suitable for processing small samples at high latitude, the extreme gradient boosting tree model has the advantage of strong fitting capability, and the fused model has the advantages of both the support vector machine model and the extreme gradient boosting treemodel, so that the model generalization capability is stronger, the recognition precision is higher, and the model training time in deep learning is reduced.

Description

technical field [0001] The invention belongs to the technical field of radar, and in particular relates to a radar human motion state classification algorithm and system based on model fusion. Background technique [0002] Compared with other sensors, radar has great advantages in detecting human motion status. For example, optical sensors are easily affected by weather environment and light, while radar can work all day and all day. In addition, the radar has a certain penetrating ability, which can detect the target behind the obstacle, and even judge the movement state of the human body behind the obstacle. Combined with related technologies, it can be used for anti-terrorism, military and post-disaster rescue, and life detection. . In a word, the classification of human motion state based on radar has a very broad application prospect. [0003] Beginning in the 1990s, researchers began to study human body micro-movements based on the micro-Doppler characteristics of ra...

AI Technical Summary

Problems solved by technology

Chen V.C established a human body model and simulated the simulated radar echo data through software, and then performed time-frequency analysis on the simulated radar echo data, and compared and analyzed the micro-Doppler characteristic differences of the limbs of the model under different motion states; ChiehPing Lai et al. In view of the shortcomings of the traditional time-frequency analysis method for non-stationary signal processing, the Hilbert-Huang transform is introduced to extract the micro-Doppler features of the human body from complex echo signals, but the calculation and processing time is relatively long; Javier et al. use linear prediction Coding studied the classification of various human activities based on micro-Doppler features, and proposed a method to extract micro-Doppler features mixed with different frequencies, with a classification accuracy of 85%

[0004] Most of the existing machine learning-based human motion state classification methods use a single classifier, which will result in insufficient generalization ability of the model and relatively low recognition accuracy

In deep learning, the complexity of the model is very high, the amount of calculation is too large, and the training data set is not easy to collect; the training of the model often takes a lot of time, and the process of automatically extracting image features by the model is not very interpretable

Images