EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A method for detecting small objects in remote sensing images based on feature enhancement and scale-adaptive optimization in complex scenarios

Xiaoxiao Wang iD, Xia Zou, Meng Sun, Chong Jia, Yongqiang Xie, Xiongwei Zhang

PLOS One · 2026

DOI: 10.1371/journal.pone.0350873 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Xiaoxiao Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Army Engineering University of PLA, Nanjing, China. Hauptthemen laut MEDLINE: Remote Sensing Technology, Image Processing, Computer-Assisted. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of small object detection in remote sensing images, such as susceptibility to background noise and difficulties in feature extraction, this paper proposes a method for detecting small objects in remote sensing images based on feature enhancement and scale-adaptive optimization under complex scenarios. First, we constructed a bidirectional complementary feature fusion network, employing a bidirectional feature fusion mechanism to enhance the interaction between shallow-level details and deep-level semantic features, thereby enabling more effective multi-scale feature fusion. Second, we developed a Multi-scale Local-Global Attention (MLGA) module that uses multi-scale pooling to capture both local details and global context, and employs dynamic weights for adaptive feature fusion, effectively suppressing background noise and highlighting the features of small objects. In addition, we designed a scale-adaptive bounding box regression loss function (SAWIoU) that addresses the scale bias issue for small objects by introducing a scale scaling factor, thereby ensuring balanced optimization across objects of different scales and further improving localization accuracy. Finally, experimental results on two public remote sensing datasets DIOR and RSOD show that the proposed method achieved mAP50 scores of 0.885 and 0.971, respectively, significantly outperforming current mainstream detection models, with particularly notable improvements in small-object detection accuracy. Additionally, ablation studies further validate the effectiveness and robustness of this method in detecting small objects in remote sensing under complex backgrounds.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Remote Sensing TechnologyImage Processing, Computer-AssistedDetection AlgorithmsAlgorithms

Autor:innen und Institutionen

  • Army Engineering University of PLA, Nanjing, China.
  • State Key Laboratory of Advanced Communication Technology, Nanjing, China.
  • Chinese People's Liberation Army Unit, Beijing, China.

ORCID-Profile: Xiaoxiao Wang

Zitieren

APA

Wang, X., Zou, X., Sun, M., Jia, C., Xie, Y., & Zhang, X. (2026). A method for detecting small objects in remote sensing images based on feature enhancement and scale-adaptive optimization in complex scenarios. PLOS One. https://doi.org/10.1371/journal.pone.0350873

Vancouver

Wang X, Zou X, Sun M, Jia C, Xie Y, Zhang X. A method for detecting small objects in remote sensing images based on feature enhancement and scale-adaptive optimization in complex scenarios. PLOS One. 2026. doi:10.1371/journal.pone.0350873

BibTeX
@article{Wang2026,
  author = {Wang, Xiaoxiao and Zou, Xia and Sun, Meng and Jia, Chong and Xie, Yongqiang and Zhang, Xiongwei},
  title = {A method for detecting small objects in remote sensing images based on feature enhancement and scale-adaptive optimization in complex scenarios},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0350873}
}
Kostenlos starten →