EUVIMEDEUVIMED entdecken
Crossref

Structure-Aware Generative Modeling and Comprehensive Evaluation for High-Fidelity Radar HRRP Synthesis

Shuai Li, Wentao Li, Junyan Chen, Biao Tian, Shiyou Xu

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 2511518-2511518

DOI: 10.1109/tim.2026.3697051 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Shuai Li und 4 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Science and Technology Program, Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution range profile (HRRP) precisely characterizes radar scattering properties of distant targets, providing critical physical information for accurate detection and identification. However, the limited availability and high acquisition cost of real-world HRRP data pose significant challenges for reliable modeling and simulation in measurement systems. To address these limitations, this article introduces a structure-aware multiscale sparse generative adversarial network (SMSGAN) for high-fidelity HRRP synthesis. The proposed model is developed based on measured HRRP data and demonstrates strong modeling capability by effectively capturing global energy characteristics and localized scattering structures inherent in real radar returns. In addition, a dedicated evaluation framework is designed, integrating metrics such as distribution alignment, structural similarity, and spectral deviation, to provide a comprehensive assessment of signal quality from a radar measurement perspective. Systematic experiments based on two typical radar measured datasets show that the proposed SMSGAN model significantly outperforms comparison methods, such as diffusion and flow models, in key indicators, including distribution alignment and scattering structure fidelity.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Science and Technology Program
  • Shenzhen Science and Technology Program

Zitieren

APA

Li, S., Li, W., Chen, J., Tian, B., & Xu, S. (2026). Structure-Aware Generative Modeling and Comprehensive Evaluation for High-Fidelity Radar HRRP Synthesis. IEEE Transactions on Instrumentation and Measurement, 75, 2511518-2511518. https://doi.org/10.1109/tim.2026.3697051

Vancouver

Li S, Li W, Chen J, Tian B, Xu S. Structure-Aware Generative Modeling and Comprehensive Evaluation for High-Fidelity Radar HRRP Synthesis. IEEE Transactions on Instrumentation and Measurement. 2026;75:2511518-2511518. doi:10.1109/tim.2026.3697051

BibTeX
@article{Li2026,
  author = {Li, Shuai and Li, Wentao and Chen, Junyan and Tian, Biao and Xu, Shiyou},
  title = {Structure-Aware Generative Modeling and Comprehensive Evaluation for High-Fidelity Radar HRRP Synthesis},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {2511518--2511518},
  doi = {10.1109/tim.2026.3697051}
}
Kostenlos starten →