Skip to main navigation Skip to search Skip to main content

ERA-Net: End-to-End Recognition-Aware Sparse SAR Imaging Network

  • Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

High-resolution synthetic aperture radar (SAR) imaging is crucial for effective target recognition. Current sparse aperture SAR imaging algorithm based on compressed sensing (CS) often lack constraints related to recognition performance, leading to the loss of key features beneficial for recognition. This results in lower recognition rates in the resulting images. This paper proposes a sparse SAR imaging method driven by target recognition tasks, and constructs an end-to-end recognition-aware sparse SAR imaging network (ERA-Net) from the perspective of SAR imaging interpretation integration. It not only effectively improves the accuracy of downstream recognition tasks, but also reconstructs higher quality SAR images that are conducive to recognition.

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
Publication statusPublished - 2024
Event2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024 - Zhuhai, China
Duration: 22 Nov 2024 → 24 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
Period22/11/24 → 24/11/24

Keywords

  • SAR imaging
  • sparse reconstruction
  • target Recognition

Fingerprint

Dive into the research topics of 'ERA-Net: End-to-End Recognition-Aware Sparse SAR Imaging Network'. Together they form a unique fingerprint.

Cite this