EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Frequency-Aware Feature Pyramid Framework for Contextual Representation in Remote Sensing Object Detection

Lingyun Gu, Qingyun Fang, Eugene Popov, Vitalii Pavlov, Sergey Volvenko, Sergey Makarov, Ge Dong

Astronautics · 2026

DOI: 10.3390/astronautics1010005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Astronautics, 2026. Verfasst von Lingyun Gu und 6 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council, Peter the Great St.Petersburg Polytechnic University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing object detection is a critical task in Earth observation. Despite the remarkable progress made in general object detection, existing detectors struggle with remote sensing scenarios due to the prevalence of numerous small objects with limited discriminative cues. Cutting-edge studies have shown that incorporating contextual information effectively enhances the detection performance for small objects. Meanwhile, recent research has revealed that convolution in the frequency domain is capable of capturing long-range spatial dependencies with high efficiency. Inspired by this, we propose a Frequency-aware Feature Pyramid Framework (FFPF) for remote sensing object detection, which consists of a novel Frequency-aware ResNet (F-ResNet) and a Bilateral Spectral-aware Feature Pyramid Network (BS-FPN). Specifically, the F-ResNet is proposed to extract the spectral context information by plugging the frequency domain convolution into each stage of the backbone, thereby enriching features of small objects. In addition, the BS-FPN employs a bilateral sampling strategy and skipping connection to model the association of object features at different scales, enabling the contextual information extracted by the F-ResNet to be fully leveraged. Extensive experiments are conducted for object detection in the public remote sensing image dataset and natural image dataset. The experimental results demonstrate the excellent performance of the FFPF, achieving 73.8% mAP on the DIOR dataset without using any additional training tricks.

Förderung

  • China Scholarship Council
  • Peter the Great St.Petersburg Polytechnic University

Zitieren

APA

Gu, L., Fang, Q., Popov, E., Pavlov, V., Volvenko, S., Makarov, S., & Dong, G. (2026). Frequency-Aware Feature Pyramid Framework for Contextual Representation in Remote Sensing Object Detection. Astronautics. https://doi.org/10.3390/astronautics1010005

Vancouver

Gu L, Fang Q, Popov E, Pavlov V, Volvenko S, Makarov S, et al. Frequency-Aware Feature Pyramid Framework for Contextual Representation in Remote Sensing Object Detection. Astronautics. 2026. doi:10.3390/astronautics1010005

BibTeX
@article{Gu2026,
  author = {Gu, Lingyun and Fang, Qingyun and Popov, Eugene and Pavlov, Vitalii and Volvenko, Sergey and Makarov, Sergey and Dong, Ge},
  title = {Frequency-Aware Feature Pyramid Framework for Contextual Representation in Remote Sensing Object Detection},
  journal = {Astronautics},
  year = {2026},
  doi = {10.3390/astronautics1010005}
}
Kostenlos starten →