MMFNet: A Mamba-Based Multimodal Fusion Network for Remote Sensing Image Semantic Segmentation
Sensors · 08.10.2025 · 25 (19) · 6225
DOI: 10.3390/s25196225 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 08.10.2025. Verfasst von Jingting Qiu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Earth and Planetary Sciences, Chengdu University of Technology, Chengdu 610059, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Science and Technology Project of Sichuan Bureau of Geology & Mineral Resources, the Academic Degree and Postgraduate Education Reform Project of Sichuan Province, Science and Technology Project of Sichuan Bureau of Geology & Mineral Resources.
Abstract (Originalsprache)
Accurate semantic segmentation of high-resolution remote sensing imagery is challenged by substantial intra-class variability, inter-class similarity, and the limitations of single-modality data. This paper proposes MMFNet, a novel multimodal fusion network that leverages the Mamba architecture to efficiently capture long-range dependencies for semantic segmentation tasks. MMFNet adopts a dual-encoder design, combining ResNet-18 for local detail extraction and VMamba for global contextual modelling, striking a balance between segmentation accuracy and computational efficiency. A Multimodal Feature Fusion Block (MFFB) is introduced to effectively integrate complementary information from optical imagery and digital surface models (DSMs), thereby enhancing multimodal feature interaction and improving segmentation accuracy. Furthermore, a frequency-aware upsampling module (FreqFusion) is incorporated in the decoder to enhance boundary delineation and recover fine spatial details. Extensive experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that MMFNet achieves mean IoU scores of 83.50% and 86.06%, outperforming eight state-of-the-art methods while maintaining relatively low computational complexity. These results highlight MMFNet’s potential for efficient and accurate multimodal semantic segmentation in remote sensing applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Earth and Planetary Sciences, Chengdu University of Technology, Chengdu 610059, China.
- Qi-Liang Spatiotemporal Information Innovation Studio, The 9th Geological Brigade of Sichuan Province, Deyang 618029, China.
- Geographic Information and Geological Environment Key Laboratory of Deyang City, Deyang 618029, China.
ORCID-Profile: Ronghao Yang
Förderung
- the Science and Technology Project of Sichuan Bureau of Geology & Mineral Resources
- the Academic Degree and Postgraduate Education Reform Project of Sichuan Province
- Science and Technology Project of Sichuan Bureau of Geology & Mineral Resources
- Academic Degree and Postgraduate Education Reform Project of Sichuan Province
Zitieren
APA
Qiu, J., Chang, W., Ren, W., Hou, S., & Yang, R. (2025). MMFNet: A Mamba-Based Multimodal Fusion Network for Remote Sensing Image Semantic Segmentation. Sensors, 25(19), 6225. https://doi.org/10.3390/s25196225
Vancouver
Qiu J, Chang W, Ren W, Hou S, Yang R. MMFNet: A Mamba-Based Multimodal Fusion Network for Remote Sensing Image Semantic Segmentation. Sensors. 2025;25(19):6225. doi:10.3390/s25196225
BibTeX
@article{Qiu2025,
author = {Qiu, Jingting and Chang, Wei and Ren, Wei and Hou, Shanshan and Yang, Ronghao},
title = {MMFNet: A Mamba-Based Multimodal Fusion Network for Remote Sensing Image Semantic Segmentation},
journal = {Sensors},
year = {2025},
volume = {25},
number = {19},
pages = {6225},
doi = {10.3390/s25196225}
}
EUVIMED