MGF-GCN: Multimodal interaction Mamba-aided graph convolutional fusion network for semantic segmentation of remote sensing images

计算机科学 图形 分割 卷积神经网络 融合 人工智能 模式识别(心理学) 计算机视觉 理论计算机科学 语言学 哲学
作者
Yanfeng Zhao,Linwei Qiu,Zhenjian Yang,Yadong Chen,Yunjie Zhang
出处
期刊:Information Fusion [Elsevier BV]
卷期号:122: 103150-103150 被引量:11
标识
DOI:10.1016/j.inffus.2025.103150
摘要

With the continuous improvement of the spatial resolution of remote sensing images, the application of semantic segmentation to high-resolution remote sensing data has made significant progress. However, due to the limited information provided by unimodal data and the similarity or confusion between different types of objects in complex scenes, the performance of unimodal segmentation models remains limited. To address these challenges, this paper proposes a multimodal semantic segmentation network that combines visible light data (RGB/IRRG) with digital surface model (DSM) data to provide richer object information . We employ different backbone networks to process visible light and DSM data separately and design a Height-Aware Graph Convolution (HAGC) strategy to effectively capture the spatial correlations between the two modalities. Additionally, we introduce a Multimodal Hierarchical Interaction Mamba (MHIMamba) module to fuse and process features from different modalities, achieving feature complementarity and enhancing segmentation performance . Finally, we apply a Progressive Context Cascade Decoder (PCCD) to recover spatial details . This work pioneers the integration of the Mamba into multimodal semantic segmentation, facilitating effective cross-modal feature interaction and improving segmentation accuracy in remote sensing imagery . Experimental results demonstrate that our model achieves state-of-the-art segmentation performance on the Potsdam and Vaihingen datasets. Our code is available at https://github.com/zyf-cell/MGF-GCN . • DGCN backbone with Height-Aware Graph Convolution boosts height perception. • MHIMamba fuses multimodal features in shared space for better performance. • Progressive Context Cascade Decoder refines multilevel features.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
egfuy完成签到,获得积分10
1秒前
molihuakai应助abc采纳,获得10
2秒前
2秒前
手打鱼丸完成签到 ,获得积分10
3秒前
海絮关注了科研通微信公众号
4秒前
5秒前
6秒前
爆米花应助1234采纳,获得10
8秒前
8秒前
10秒前
12秒前
iq_lv完成签到,获得积分10
13秒前
973382868发布了新的文献求助10
14秒前
14秒前
14秒前
烟花应助踏实的土豆采纳,获得10
14秒前
15秒前
15秒前
16秒前
王甜甜完成签到,获得积分20
16秒前
16秒前
17秒前
17秒前
egfuy发布了新的文献求助10
18秒前
18秒前
19秒前
852应助973382868采纳,获得10
19秒前
爆米花应助史萌采纳,获得10
20秒前
20秒前
CodeCraft应助活泼的稀采纳,获得10
20秒前
21秒前
CipherSage应助hj1234采纳,获得10
21秒前
21秒前
无莞发布了新的文献求助30
22秒前
科研通AI2S应助Sun采纳,获得10
23秒前
水告完成签到,获得积分10
23秒前
24秒前
24秒前
薯条发布了新的文献求助10
25秒前
25秒前
高分求助中
Clinical Epidemiology: The Essentials, 6e 10000
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
The Graphene Handbook (2019 Edition) 800
Adhesion Science: Principles & Practice 800
Signals, Systems, and Signal Processing 610
Fundamentals of Pharmaceutical and Biologics Regulations: A Global Perspective, Second Edition 600
The Immune System (Fifth Edition) 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 物理 内科学 复合材料 催化作用 物理化学 光电子学 电极 细胞生物学 基因 无机化学
热门帖子
关注 科研通微信公众号,转发送积分 6567788
求助须知:如何正确求助?哪些是违规求助? 8347557
关于积分的说明 17884843
捐赠科研通 5694371
什么是DOI,文献DOI怎么找? 2943911
邀请新用户注册赠送积分活动 1919816
关于科研通互助平台的介绍 1795530