EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images

Xin Li, Feng Xu, Xi Yong, Deqing Chen, Runliang Xia, Baoliu Ye, Hongmin Gao, Ziqi Chen, Xin Lyu

Remote Sensing · 03.12.2023 · 15 (23) · 5610

DOI: 10.3390/rs15235610 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.12.2023. Verfasst von Xin Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: High-Resolution Earth Observing System—Water Application Demonstration, Special Funds for Basic Research Operating Expenses of Central-level Public Welfare Research Institutes, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation plays a pivotal role in the intelligent interpretation of remote sensing images (RSIs). However, conventional methods predominantly focus on learning representations within the spatial domain, often resulting in suboptimal discriminative capabilities. Given the intrinsic spectral characteristics of RSIs, it becomes imperative to enhance the discriminative potential of these representations by integrating spectral context alongside spatial information. In this paper, we introduce the spectrum-space collaborative network (SSCNet), which is designed to capture both spectral and spatial dependencies, thereby elevating the quality of semantic segmentation in RSIs. Our innovative approach features a joint spectral–spatial attention module (JSSA) that concurrently employs spectral attention (SpeA) and spatial attention (SpaA). Instead of feature-level aggregation, we propose the fusion of attention maps to gather spectral and spatial contexts from their respective branches. Within SpeA, we calculate the position-wise spectral similarity using the complex spectral Euclidean distance (CSED) of the real and imaginary components of projected feature maps in the frequency domain. To comprehensively calculate both spectral and spatial losses, we introduce edge loss, Dice loss, and cross-entropy loss, subsequently merging them with appropriate weighting. Extensive experiments on the ISPRS Potsdam and LoveDA datasets underscore SSCNet’s superior performance compared with several state-of-the-art methods. Furthermore, an ablation study confirms the efficacy of SpeA.

Förderung

  • High-Resolution Earth Observing System—Water Application Demonstration
  • Special Funds for Basic Research Operating Expenses of Central-level Public Welfare Research Institutes
  • National Natural Science Foundation of China
  • Excellent Post-doctoral Program of Jiangsu Province
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Li, X., Xu, F., Yong, X., Chen, D., Xia, R., Ye, B., Gao, H., Chen, Z., & Lyu, X. (2023). SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images. Remote Sensing, 15(23), 5610. https://doi.org/10.3390/rs15235610

Vancouver

Li X, Xu F, Yong X, Chen D, Xia R, Ye B, et al. SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images. Remote Sensing. 2023;15(23):5610. doi:10.3390/rs15235610

BibTeX
@article{Li2023,
  author = {Li, Xin and Xu, Feng and Yong, Xi and Chen, Deqing and Xia, Runliang and Ye, Baoliu and Gao, Hongmin and Chen, Ziqi and Lyu, Xin},
  title = {SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {23},
  pages = {5610},
  doi = {10.3390/rs15235610}
}
Kostenlos starten →