EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tiny Object Detection via Normalized Gaussian Label Assignment and Multi-Scale Hybrid Attention

Shihao Lin, Li Zhong, Si Chen, Da-Han Wang

Remote Sensing · 24.01.2026 · 18 (3) · 396

DOI: 10.3390/rs18030396 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.01.2026. Verfasst von Shihao Lin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Xiamen, Unveiling and Leading Projects of Xiamen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid development of Convolutional Neural Networks (CNNs) has markedly boosted the performance of object detection in remote sensing. Nevertheless, tiny objects typically account for an extremely small fraction of the total area in remote sensing images, rendering existing IoU-based or area-based evaluation metrics highly sensitive to minor pixel deviations. Meanwhile, classic detection models face inherent bottlenecks in efficiently mining discriminative features for tiny objects, leaving the task of tiny object detection in remote sensing images as an ongoing challenge in this field. To alleviate these issues, this paper proposes a tiny object detection method based on Normalized Gaussian Label Assignment and Multi-scale Hybrid Attention. Firstly, 2D Gaussian modeling is performed on the feature receptive field and the actual bounding box, using Normalized Bhattacharyya Distance for precise similarity measurement. Furthermore, a candidate sample quality ranking mechanism is constructed to select high-quality positive samples. Finally, a Multi-scale Hybrid Attention module is designed to enhance the discriminative feature extraction of tiny objects. The proposed method achieves 25.7% and 27.9% AP on the AI-TOD-v2 and VisDrone2019 datasets, respectively, significantly improving the detection capability of tiny objects in complex remote sensing scenarios.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Xiamen
  • Unveiling and Leading Projects of Xiamen
  • Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City

Zitieren

APA

Lin, S., Zhong, L., Chen, S., & Wang, D. (2026). Tiny Object Detection via Normalized Gaussian Label Assignment and Multi-Scale Hybrid Attention. Remote Sensing, 18(3), 396. https://doi.org/10.3390/rs18030396

Vancouver

Lin S, Zhong L, Chen S, Wang D. Tiny Object Detection via Normalized Gaussian Label Assignment and Multi-Scale Hybrid Attention. Remote Sensing. 2026;18(3):396. doi:10.3390/rs18030396

BibTeX
@article{Lin2026,
  author = {Lin, Shihao and Zhong, Li and Chen, Si and Wang, Da-Han},
  title = {Tiny Object Detection via Normalized Gaussian Label Assignment and Multi-Scale Hybrid Attention},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {3},
  pages = {396},
  doi = {10.3390/rs18030396}
}
Kostenlos starten →