EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale Feature Fusion Network with Symmetric Attention for Land Cover Classification Using SAR and Optical Images

Dongdong Xu, Zheng Li, Hao Feng, Fanlu Wu, Yongcheng Wang

Remote Sensing · 08.03.2024 · 16 (6) · 957

DOI: 10.3390/rs16060957 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 08.03.2024. Verfasst von Dongdong Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The complementary characteristics of SAR and optical images are beneficial in improving the accuracy of land cover classification. Deep learning-based models have achieved some notable results. However, how to effectively extract and fuse the unique features of multi-modal images for pixel-level classification remains challenging. In this article, a two-branch supervised semantic segmentation framework without any pretrained backbone is proposed. Specifically, a novel symmetric attention module is designed with improved strip pooling. The multiple long receptive fields can better perceive irregular objects and obtain more anisotropic contextual information. Meanwhile, to solve the semantic absence and inconsistency of different modalities, we construct a multi-scale fusion module, which is composed of atrous spatial pyramid pooling, varisized convolutions and skip connections. A joint loss function is introduced to constrain the backpropagation and reduce the impact of class imbalance. Validation experiments were implemented on the DFC2020 and WHU-OPT-SAR datasets. The proposed model achieved the best quantitative values on the metrics of OA, Kappa and mIoU, and its class accuracy was also excellent. It is worth mentioning that the number of parameters and the computational complexity of the method are relatively low. The adaptability of the model was verified on RGB–thermal segmentation task.

Förderung

  • National Key R&D Program of China

Zitieren

APA

Xu, D., Li, Z., Feng, H., Wu, F., & Wang, Y. (2024). Multi-Scale Feature Fusion Network with Symmetric Attention for Land Cover Classification Using SAR and Optical Images. Remote Sensing, 16(6), 957. https://doi.org/10.3390/rs16060957

Vancouver

Xu D, Li Z, Feng H, Wu F, Wang Y. Multi-Scale Feature Fusion Network with Symmetric Attention for Land Cover Classification Using SAR and Optical Images. Remote Sensing. 2024;16(6):957. doi:10.3390/rs16060957

BibTeX
@article{Xu2024,
  author = {Xu, Dongdong and Li, Zheng and Feng, Hao and Wu, Fanlu and Wang, Yongcheng},
  title = {Multi-Scale Feature Fusion Network with Symmetric Attention for Land Cover Classification Using SAR and Optical Images},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {6},
  pages = {957},
  doi = {10.3390/rs16060957}
}
Kostenlos starten →