EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semantic Segmentation of Satellite Images for Landslide Detection Using Foreground-Aware and Multi-Scale Convolutional Attention Mechanism

Chih-Chang Yu iD, Yuan-Di Chen, Hsu-Yung Cheng iD, Chi-Lun Jiang

Sensors · 10.10.2024 · 24 (20) · 6539

DOI: 10.3390/s24206539 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.10.2024. Verfasst von Chih-Chang Yu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Computer Engineering, Chung Yuan Christian University, Taoyuan City 320, Taiwan. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, Taiwan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advancements in satellite and aerial imagery technology have made it easier to obtain high-resolution remote sensing images, leading to widespread research and applications in various fields. Remote sensing image semantic segmentation is a crucial task that provides semantic and localization information for target objects. In addition to the large-scale variation issues common in most semantic segmentation datasets, aerial images present unique challenges, including high background complexity and imbalanced foreground–background ratios. However, general semantic segmentation methods primarily address scale variations in natural scenes and often neglect the specific challenges in remote sensing images, such as inadequate foreground modeling. In this paper, we present a foreground-aware remote sensing semantic segmentation model. The model introduces a multi-scale convolutional attention mechanism and utilizes a feature pyramid network architecture to extract multi-scale features, addressing the multi-scale problem. Additionally, we introduce a Foreground–Scene Relation Module to mitigate false alarms. The model enhances the foreground features by modeling the relationship between the foreground and the scene. In the loss function, a Soft Focal Loss is employed to focus on foreground samples during training, alleviating the foreground–background imbalance issue. Experimental results indicate that our proposed method outperforms current state-of-the-art general semantic segmentation methods and transformer-based methods on the LS dataset benchmark.

Schlagwörter

Stichwörter der Autor:innen

convolutional attention mechanismmulti-scale features fusionremote sensingsemantic segmentation

Autor:innen und Institutionen

  • Department of Information and Computer Engineering, Chung Yuan Christian University, Taoyuan City 320, Taiwan.
  • Department of Computer Science and Information Engineering, National Central University, Taoyuan City 320, Taiwan.

ORCID-Profile: Chih-Chang Yu, Hsu-Yung Cheng

Förderung

  • National Science and Technology Council, Taiwan

Zitieren

APA

Yu, C. C., Chen, Y. D., Cheng, H. Y., & Jiang, C. L. (2024). Semantic Segmentation of Satellite Images for Landslide Detection Using Foreground-Aware and Multi-Scale Convolutional Attention Mechanism. Sensors, 24(20), 6539. https://doi.org/10.3390/s24206539

Vancouver

Yu CC, Chen YD, Cheng HY, Jiang CL. Semantic Segmentation of Satellite Images for Landslide Detection Using Foreground-Aware and Multi-Scale Convolutional Attention Mechanism. Sensors. 2024;24(20):6539. doi:10.3390/s24206539

BibTeX
@article{Yu2024,
  author = {Yu, Chih-Chang and Chen, Yuan-Di and Cheng, Hsu-Yung and Jiang, Chi-Lun},
  title = {Semantic Segmentation of Satellite Images for Landslide Detection Using Foreground-Aware and Multi-Scale Convolutional Attention Mechanism},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {20},
  pages = {6539},
  doi = {10.3390/s24206539}
}
Kostenlos starten →