Real‐time recognition of human motions using multidimensional features in ultrawideband biological radar

Abstract Human motion recognition for biological radar has made astonishing progress. However, in some applications with high real‐time requirements, it is difficult for existing approaches to achieve high accuracy. A multidimensional features long short‐term memory (LSTM) neural network model is pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinxiao Zhong, Liangnian Jin, Qiang Mao
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:IET Biometrics
Online Access:https://doi.org/10.1049/bme2.12038
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832559625848750080
author Jinxiao Zhong
Liangnian Jin
Qiang Mao
author_facet Jinxiao Zhong
Liangnian Jin
Qiang Mao
author_sort Jinxiao Zhong
collection DOAJ
description Abstract Human motion recognition for biological radar has made astonishing progress. However, in some applications with high real‐time requirements, it is difficult for existing approaches to achieve high accuracy. A multidimensional features long short‐term memory (LSTM) neural network model is presented using multibranch network structure and high‐dimensional radar feature fusion, which can recognise motions of human in real time, even in the presence of occlusions. The features selected for motion recognition including slow time range‐map and slow time Doppler map. A single feature‐based representation is not enough to capture the variations and attributes of individuals (range, velocity, etc.); thus, the fusion of multiple features is significant for recognising motions. Furthermore, because action reflects the behaviour of a human within a period, and the start and end are unavailable, intercepting fixed‐length data in the time domain for recognition is not feasible. Thus, we introduce an approach based on an LSTM network that extracts features along the time dimension. Experiments show that the proposed approach is effective. A recognition accuracy of above 93.38% is achieved.
format Article
id doaj-art-63ee274959c7413494ebaa8fe77729e7
institution Kabale University
issn 2047-4938
2047-4946
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series IET Biometrics
spelling doaj-art-63ee274959c7413494ebaa8fe77729e72025-02-03T01:29:36ZengWileyIET Biometrics2047-49382047-49462022-01-011111910.1049/bme2.12038Real‐time recognition of human motions using multidimensional features in ultrawideband biological radarJinxiao Zhong0Liangnian Jin1Qiang Mao2Institute of Information and Communication Guilin University of Electronic Technology Guilin ChinaInstitute of Information and Communication Guilin University of Electronic Technology Guilin ChinaInstitute of Information and Communication Guilin University of Electronic Technology Guilin ChinaAbstract Human motion recognition for biological radar has made astonishing progress. However, in some applications with high real‐time requirements, it is difficult for existing approaches to achieve high accuracy. A multidimensional features long short‐term memory (LSTM) neural network model is presented using multibranch network structure and high‐dimensional radar feature fusion, which can recognise motions of human in real time, even in the presence of occlusions. The features selected for motion recognition including slow time range‐map and slow time Doppler map. A single feature‐based representation is not enough to capture the variations and attributes of individuals (range, velocity, etc.); thus, the fusion of multiple features is significant for recognising motions. Furthermore, because action reflects the behaviour of a human within a period, and the start and end are unavailable, intercepting fixed‐length data in the time domain for recognition is not feasible. Thus, we introduce an approach based on an LSTM network that extracts features along the time dimension. Experiments show that the proposed approach is effective. A recognition accuracy of above 93.38% is achieved.https://doi.org/10.1049/bme2.12038
spellingShingle Jinxiao Zhong
Liangnian Jin
Qiang Mao
Real‐time recognition of human motions using multidimensional features in ultrawideband biological radar
IET Biometrics
title Real‐time recognition of human motions using multidimensional features in ultrawideband biological radar
title_full Real‐time recognition of human motions using multidimensional features in ultrawideband biological radar
title_fullStr Real‐time recognition of human motions using multidimensional features in ultrawideband biological radar
title_full_unstemmed Real‐time recognition of human motions using multidimensional features in ultrawideband biological radar
title_short Real‐time recognition of human motions using multidimensional features in ultrawideband biological radar
title_sort real time recognition of human motions using multidimensional features in ultrawideband biological radar
url https://doi.org/10.1049/bme2.12038
work_keys_str_mv AT jinxiaozhong realtimerecognitionofhumanmotionsusingmultidimensionalfeaturesinultrawidebandbiologicalradar
AT liangnianjin realtimerecognitionofhumanmotionsusingmultidimensionalfeaturesinultrawidebandbiologicalradar
AT qiangmao realtimerecognitionofhumanmotionsusingmultidimensionalfeaturesinultrawidebandbiologicalradar