EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive Spatial–Frequency Information Fusion for SAR Ship Detection

Zhengju Xiao, Xiaolong Zheng, Dongdong Guan, Qisong Yang, Zhengsheng Chen, Lijiale Yang

Remote Sensing · 10.08.2026 · 18 (16) · 2687

DOI: 10.3390/rs18162687 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.08.2026. Verfasst von Zhengju Xiao und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shaanxi Provincial Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Synthetic-aperture radar (SAR) ship detection is a fundamental task in maritime remote sensing, supporting wide-area surveillance, traffic monitoring, and emergency response under all-weather imaging conditions. Existing deep detectors mainly rely on spatial cues such as intensity, shape and context, but structured sea clutter and near-shore interference can still produce ship-like responses, while fine scattering details are weakened by deep downsampling. We address two practical representation limitations: incomplete preservation of shallow high-resolution details, and limited explicit modeling of local directional variation. To this end, we propose HMF-RTMDet, a shallow-neck spatial–frequency fusion detector. A P2 high-resolution path combines C2 features with upsampled P3 semantics. HybridMFBlock then processes the fused feature through a morphology branch and a trainable depthwise branch initialized by fractional Gabor templates, followed by channel-wise fusion. In the reported main HRSID run, HMF-RTMDet improves RTMDet-s from 67.9% to 72.6% in AP50:95, from 90.2% to 94.2% in AP50, and from 68.2% to 73.4% in APs. Across three runs, however, its AP50:95 is 72.17 ± 0.38%, comparable to the SFS-Conv and MCU-only controls. The evidence therefore identifies the P2 path as the main gain source but does not establish a stable advantage for HybridMFBlock over these controls. On SSDD, overall AP50:95 remains nearly unchanged and large-target performance decreases, defining an important boundary of the current design.

Förderung

  • National Natural Science Foundation of China
  • Shaanxi Provincial Natural Science Foundation

Zitieren

APA

Xiao, Z., Zheng, X., Guan, D., Yang, Q., Chen, Z., & Yang, L. (2026). Adaptive Spatial–Frequency Information Fusion for SAR Ship Detection. Remote Sensing, 18(16), 2687. https://doi.org/10.3390/rs18162687

Vancouver

Xiao Z, Zheng X, Guan D, Yang Q, Chen Z, Yang L. Adaptive Spatial–Frequency Information Fusion for SAR Ship Detection. Remote Sensing. 2026;18(16):2687. doi:10.3390/rs18162687

BibTeX
@article{Xiao2026,
  author = {Xiao, Zhengju and Zheng, Xiaolong and Guan, Dongdong and Yang, Qisong and Chen, Zhengsheng and Yang, Lijiale},
  title = {Adaptive Spatial–Frequency Information Fusion for SAR Ship Detection},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {16},
  pages = {2687},
  doi = {10.3390/rs18162687}
}
Kostenlos starten →