A maneuvering tracking method based on LSTM and CS model

Siwei Li, Cheng Hu, Rui Wang, Chao Zhou, Jing Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Maneuvering target tracking is an important research field in radar tracking. In recent years, the development of machine learning provides a new idea for maneuvering target tracking. This paper presents a trajectory recognition method based on LSTM (Long Short-Term Memory) and a maneuvering tracking method using matched CS (current statistics) model parameter. This method makes use of the characteristics of LSTM that can effectively combine the above information to realize the recognition of target motion states. Then, clustering analysis is used to obtain the optimal filtering parameters of each motion mode in the statistical sense, and filtering is carried out according to the recognition results of LSTM. Compared with the traditional maneuvering tracking method, this method can maintain stable filtering gain in the duration of maneuvering, and the filtering accuracy is improved.

Original languageEnglish
Title of host publicationICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728123455
DOIs
Publication statusPublished - Dec 2019
Event2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019 - Chongqing, China
Duration: 11 Dec 201913 Dec 2019

Publication series

NameICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019

Conference

Conference2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019
Country/TerritoryChina
CityChongqing
Period11/12/1913/12/19

Keywords

  • CS model
  • Long Short-Term Memory
  • maneuvering target tracking
  • trajectory recognition

Fingerprint

Dive into the research topics of 'A maneuvering tracking method based on LSTM and CS model'. Together they form a unique fingerprint.

Cite this