摘要
【目的】随着空间分辨率的提高,遥感图像所蕴含的信息越来越复杂,其中包含了大量的空间特征与语义特征,而二者的有效提取融合对于语义分割的效果起到关键性作用,然而,大多数现有方法只关注特征融合部分的研究改进,而没有考虑空间语义特征的一致性,导致了边缘分割不完整等问题。此外,这些方法往往忽略了边缘信息的精确提取。上述这些问题将会严重影响分割的准确性。【方法】本文提出了一种基于多尺度深度监督的高分辨遥感图像语义分割模型。首先,针对空间与语义特征分别设计不同的特征提取分支,充分利用遥感图像的空间和语义信息;其次,在空间分支中加入本文所提出的空间去冗余残差模块,引入小波变换与坐标卷积,更加有针对性地提取空间特征,并更好地关注边缘特征;然后,在语义分支中加入本文所提出的残差注意力Mamba,实现了对于全局层次的语义特征提取;最后,在特征融合部分采用多尺度特征融合机制,设计大内核分组特征提取模块将空间分支、语义分支特征与深层次特征逐层融合,抑制无效特征,激活有效特征。此外,本模型采用深度监督机制,对各个阶段的特征融合层添加辅助监督头,提高训练效率。【结果】本文在ISPRS Potsdam和随机采样裁剪数据增强后的Vaihingen数据集上进行了对比实验与消融实验,结果表明本文所提出算法在ISPRS Potsdam和随机采样裁剪数据增强后的Vaihingen数据集上的平均交并比达到83.43%和86.49%,与其他9种最新的核心方法相比,如CGGLNet、CMLFormer等,在平均交并比指标上分别至少提高了5.00%和3.00%。【结论】本文算法能够有效地提取空间语义特征,并将其有效融合,提高了遥感图像语义分割的准确率。
[Objectives] With the enhancement of spatial resolution, remote sensing images contain increasingly intricate information, encompassing a vast array of spatial and semantic features. The effective extraction and integration of these features play a pivotal role in semantic segmentation performance. However, most existing approaches focus solely on feature fusion improvements while neglecting the consistency between spatial and semantic features. Additionally, these methods often overlook the precise extraction of edge information, which significantly impacts segmentation accuracy. [Methods] This paper proposes a semantic segmentation model for high-resolution remote sensing images based on multi-scale deep supervision. First, separate feature extraction branches are designed for spatial and semantic features to fully exploit their respective information. Second, a spatial redundancy reduction residual module is incorporated into the spatial branch, integrating wavelet transformation and coordinate convolution to enhance spatial feature extraction and better capture edge details. Third, a residual attention Mamba module is added to the semantic branch to facilitate global-level semantic feature extraction. Finally, a multi-scale feature fusion mechanism is applied, utilizing a large-kernel grouped feature extraction module to progressively merge spatial, semantic, and deep-level features while suppressing irrelevant information and activating meaningful features. Additionally, a deep supervision mechanism is employed by introducing auxiliary supervision heads at each feature fusion stage to enhance training efficiency. [Results] Comparison and ablation experiments were conducted on the ISPRS Potsdam and Vaihingen datasets with random sampling and data augmentation, The experimental results demonstrate that the proposed algorithm achieves an average Intersection over Union (IoU) of 83.43% on ISPRS Potsdam and 86.49% on the augmented Vaihingen dataset. Compared to nine state-of-the-art methods, including CGGLNet and CMLFormer, the proposed approach improves the average IoU by at least 5.00% and 3.00%, respectively. [Conclusions] The results verify that the proposed algorithm effectively extracts and integrates spatial and semantic features, thereby enhancing the accuracy of semantic segmentation in remote sensing images.
作者
单慧琳
王兴涛
刘文星
吴心悦
高润泽
李红旭
SHAN Huilin;WANG Xingtao;LIU Wenxing;WU Xinyue;GAO Runze;LI Hongxu(School of Electronic and Information Engineering,Wuxi College,Wuxi 214105,China;School of Electronic and Information Engineering,Nanjing University of Information Science&Technology,Nanjing 210044,China)
出处
《地球信息科学学报》
北大核心
2025年第6期1381-1400,共20页
Journal of Geo-information Science
基金
国家自然科学基金项目(62071240、62106111)
无锡市“太湖之光”科技攻关(基础研究)项目(K20241047)。
关键词
遥感图像分割
小波变换
Mamba
多分支特征提取
多尺度特征融合
注意力机制
remote sensing image segmentation
Wavelet transform
Mamba
multi-branch feature extraction
multi-scale featurefusion
transformer
作者简介
单慧琳(1981-),女,湖北恩施人,副教授,主要从事图像处理与人工智能研究。E-mail:shanhuilin@nuist.edu.cn;通信作者:李红旭(1991-),男,河南南阳人,博士,讲师,主要从事信号与信息处理研究。E-mail:hongxuli@cwxu.edu.cn。
