Skip to main navigation Skip to search Skip to main content

Micro-Doppler Shift Compensation for Ballistic Targets Based on Residual Network ResNet50

  • Rongzheng Zhang*
  • , Yong Wang
  • *Corresponding author for this work
  • School of Electronics and Information Engineering, Harbin Institute of Technology

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

Abstract

During the mid-flight of a ballistic target, there are two types of motions: high-speed translational motion and micro-motion. Since the translational motion causes the Doppler curve to be shifted and tilted, the translational component needs to be compensated. In this paper, a new micro-Doppler shift compensation method for ballistic targets based on Residual Network ResNet50 is proposed. The micro-Doppler compensation is converted into a regression analysis of radial motion parameters, and the regression analysis is carried out using ResNet50. According to the results of simulation experiments, the algorithm can realize the compensation of translational components.

Original languageEnglish
Title of host publicationIEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331515669
DOIs
StatePublished - 2024
Externally publishedYes
Event2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024 - Zhuhai, China
Duration: 22 Nov 202424 Nov 2024

Publication series

NameIEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

Conference

Conference2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
Country/TerritoryChina
CityZhuhai
Period22/11/2424/11/24

Keywords

  • ResNet50
  • ballistic target
  • micro-Doppler
  • translation compensation

Fingerprint

Dive into the research topics of 'Micro-Doppler Shift Compensation for Ballistic Targets Based on Residual Network ResNet50'. Together they form a unique fingerprint.

Cite this