Edge-Supervised Attention-Aware Fusion Network for RGB-T Semantic Segmentation
Electronics · 08.04.2025 · 14 (8) · 1489
DOI: 10.3390/electronics14081489 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 08.04.2025. Verfasst von Ming Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ningbo Municipal Major Project of Science and Technology Innovation 2025, Zhejiang Provincial Natural Science Foundation of China, Yongjiang Sci-Tech Innovation 2035.
Abstract (Originalsprache)
To address the limitations in the efficiency of modality feature fusion in existing RGB-T semantic segmentation methods, which restrict segmentation performance, this paper proposes an edge-supervised attention-aware algorithm to enhance segmentation capabilities. Firstly, we design a feature fusion module incorporating channel and spatial attention mechanisms to achieve effective complementation and enhancement of RGB-T features. Secondly, we introduce an edge-aware refinement module that processes low-level modality features using global and local attention mechanisms, obtaining fine-grained feature information through element-wise multiplication. Building on this, we design a parallel structure of dilated convolutions to extract multi-scale detail information. Additionally, an EdgeHead is introduced after the edge-aware refinement module, with edge supervision applied to further enhance edge detail capture. Finally, the optimized fused features are fed into a decoder to complete the RGB-T semantic segmentation task. Experimental results demonstrate that our algorithm achieves mean Intersection over Union (mIoU) scores of 58.52% and 85.38% on the MFNet and PST900 datasets, respectively, significantly improving the accuracy of RGB-T semantic segmentation.
Förderung
- Ningbo Municipal Major Project of Science and Technology Innovation 2025
- Zhejiang Provincial Natural Science Foundation of China
- Yongjiang Sci-Tech Innovation 2035
- National Natural Science Foundation of China
Zitieren
APA
Wang, M., Zhu, Z., Wang, Y., Tu, R., Weng, J., & Yu, X. (2025). Edge-Supervised Attention-Aware Fusion Network for RGB-T Semantic Segmentation. Electronics, 14(8), 1489. https://doi.org/10.3390/electronics14081489
Vancouver
Wang M, Zhu Z, Wang Y, Tu R, Weng J, Yu X. Edge-Supervised Attention-Aware Fusion Network for RGB-T Semantic Segmentation. Electronics. 2025;14(8):1489. doi:10.3390/electronics14081489
BibTeX
@article{Wang2025,
author = {Wang, Ming and Zhu, Zhongjie and Wang, Yuer and Tu, Renwei and Weng, Jiuxing and Yu, Xianchao},
title = {Edge-Supervised Attention-Aware Fusion Network for RGB-T Semantic Segmentation},
journal = {Electronics},
year = {2025},
volume = {14},
number = {8},
pages = {1489},
doi = {10.3390/electronics14081489}
}
EUVIMED