loading page

A Transformer Based Network Using Micro-Doppler Features for Continuous Human Motion Recognition
  • +3
  • Liubing Jiang,
  • Minyang wu,
  • Li Che,
  • Xiaoyong Xu,
  • Yujie Mu,
  • Yongman Wu
Liubing Jiang
Guilin University of Electronic Technology

Corresponding Author:[email protected]

Author Profile
Minyang wu
Guilin University of Electronic Technology
Author Profile
Li Che
Guilin University of Electronic Technology
Author Profile
Xiaoyong Xu
Guilin University of Electronic Technology
Author Profile
Yujie Mu
Guilin University of Electronic Technology
Author Profile
Yongman Wu
Guilin University of Electronic Technology
Author Profile

Abstract

Radar-based human motion recognition has received extensive attention in recent years. Most current recognition methods generate a heat map of features through simple signal processing and then feed into a classification-based neural network for recognition. Such an approach can only identify a single action. When a set of data contains information about multiple movements it can also only be recognized as a single movement. Therefore, in order to solve the problem that continuous human motion cannot be recognized, we propose a continuous action recognition method based on micro-Doppler features and Transformer, which translates the micro-Doppler features of continuous actions into machine translation tasks, and uses the idea of natural language processing (NLP) to identify continuous action.