EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Addressing Dense Small-Object Detection in Remote Sensing: An Open-Vocabulary Object Detection Framework

Menghan Ju, Yingchao Feng, Wenhui Diao, Chunbo Liu

Remote Sensing · 10.03.2026 · 18 (6) · 851

DOI: 10.3390/rs18060851 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.03.2026. Verfasst von Menghan Ju und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Science and Disruptive Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing open-vocabulary object detection focuses on identifying and localizing unseen categories within remote sensing imagery. However, constrained by characteristics such as dense target distribution, complex background interference, and drastic scale variations inherent to remote sensing scenarios, existing methods are prone to background noise interference when extracting features from dense, small target regions. This leads to weakened semantic representation and reduced localization accuracy. Therefore, we propose RS-DINO to address these challenges. Specifically: Firstly, to address the issue of small features being obscured by the background, the feature extraction module incorporates a multi-scale large-kernel attention mechanism. This expands the receptive field while enhancing local detail modelling, significantly improving the feature representation of minute targets. Secondly, a cross-modal feature fusion module employing bidirectional cross-attention achieves deep alignment between image and textual features. Subsequently, a language-guided query selection mechanism enhances detection accuracy through hybrid query strategies. Finally, to enhance the spatial sensitivity and channel adaptability of fusion features, the multimodal decoder integrates a convolutional gated feedforward network, significantly boosting the model’s robustness in dense, multi-scale scenes. Experiments on DIOR, DOTA v2.0, and NWPU-VHR10 demonstrate substantial gains, with fine-tuned RS-DINO surpassing existing methods by 3.5%, 3.7%, and 4.0% in accuracy, respectively.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Science and Disruptive Technology Program

Zitieren

APA

Ju, M., Feng, Y., Diao, W., & Liu, C. (2026). Addressing Dense Small-Object Detection in Remote Sensing: An Open-Vocabulary Object Detection Framework. Remote Sensing, 18(6), 851. https://doi.org/10.3390/rs18060851

Vancouver

Ju M, Feng Y, Diao W, Liu C. Addressing Dense Small-Object Detection in Remote Sensing: An Open-Vocabulary Object Detection Framework. Remote Sensing. 2026;18(6):851. doi:10.3390/rs18060851

BibTeX
@article{Ju2026,
  author = {Ju, Menghan and Feng, Yingchao and Diao, Wenhui and Liu, Chunbo},
  title = {Addressing Dense Small-Object Detection in Remote Sensing: An Open-Vocabulary Object Detection Framework},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {6},
  pages = {851},
  doi = {10.3390/rs18060851}
}
Kostenlos starten →