基于CBAM增强的轻量级遥感影像语义分割方法

doi:10.13474/j.cnki.11-2246.2025.1007

测绘通报 ›› 2025, Vol. 0 ›› Issue (10): 36-42.doi: 10.13474/j.cnki.11-2246.2025.1007

• 学术研究 • 上一篇

基于CBAM增强的轻量级遥感影像语义分割方法

赵效祖¹, 苟长龙¹, 杨扬²

1. 甘肃交通职业技术学院, 甘肃兰州 730207;
2. 山西省测绘地理信息院, 山西太原 030001

收稿日期:2025-05-25 发布日期:2025-10-31
作者简介:赵效祖(1979-),男,硕士,副教授,主要研究方向为工程测量、大地测量及遥感影像处理。E-mail:16791344@qq.com
基金资助:
甘肃省高等学校创新基金(2021B-463)

A lightweight remote sensing image semantic segmentation method based on CBAM enhancement

ZHAO Xiaozu¹, GOU Changlong¹, YANG Yang²

1. Gansu Vocational College of Communications, Lanzhou 730207, China;
2. Shanxi Institute of Surveying and Mapping Geographic Information, Taiyuan 030001, China

Received:2025-05-25 Published:2025-10-31

摘要/Abstract

摘要： 本文针对高分辨率遥感影像语义分割中存在的目标尺度差异大、地物边界模糊及光谱特征相似等难点,提出了一种融合多尺度特征与双重注意力的轻量级分割模型。该模型以SegNeXt为基础,在其多尺度卷积注意力网络中引入卷积块注意力模块,通过通道与空间双重注意力机制精炼特征表达;在解码阶段优化采用Hamburger结构整合中高层语义信息。基于高分二号遥感影像数据集的试验表明,相较于原始SegNeXt,该模型各项指标均有一定程度提升,尤其在处理模糊边界和线状地物类别时表现优异;该方法在保持轻量化的同时实现了精度与效率的平衡,为资源受限环境下的遥感影像实时语义解译提供了可行方案。

关键词: 遥感影像, 语义分割, 边界增强, 轻量化网络, 深度学习

Abstract: This study addresses the challenges in high-resolution remote sensing image semantic segmentation, such as large variations in object scales, blurred boundaries, and spectral similarity.A lightweight segmentation model is proposed, which integrates multi-scale features and dual attention mechanisms.The model is based on SegNeXt, incorporating a convolutional block attention module (CBAM)into its multi-scale convolutional attention network to refine feature representations through channel and spatial dual attention mechanisms.During the decoding stage, the Hamburger structure is used to integrate mid-to-high-level semantic information.Experiments on the GF-2 remote sensing image dataset show that the model achieves noticeable improvements over the original SegNeXt across various metrics, with particularly superior performance in handling fuzzy boundaries and linear feature categories.The results demonstrate that this method achieves a balance between accuracy and efficiency while maintaining a lightweight design, offering a feasible solution for real-time semantic interpretation of remote sensing images in resource-constrained environments.

Key words: remote sensing image, semantic segmentation, boundary enhancement, lightweight network, deep learning

中图分类号:

P237

赵效祖, 苟长龙, 杨扬. 基于CBAM增强的轻量级遥感影像语义分割方法[J]. 测绘通报, 2025, 0(10): 36-42.

ZHAO Xiaozu, GOU Changlong, YANG Yang. A lightweight remote sensing image semantic segmentation method based on CBAM enhancement[J]. Bulletin of Surveying and Mapping, 2025, 0(10): 36-42.

参考文献

[1] 李道纪,郭海涛,卢俊,等. 遥感影像地物分类多注意力融和U型网络法[J]. 测绘学报,2020,49(8):1051-1064. [2] 范荣双,陈洋,徐启恒,等. 基于深度学习的高分辨率遥感影像建筑物提取方法[J]. 测绘学报,2019,48(1):34-41. [3] CHEN L C,ZHU Yukun,PAPANDREOU G,et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham:Springer,2018:833-851. [4] ZHAO Hengshuang,SHI Jianping,QI Xiaojuan,et al. Pyramid scene parsing network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu:IEEE,2017:6230-6239. [5] ZHOU Bolei,ZHAO Hang,PUIG X,et al. Semantic understanding of scenes through the ADE20K dataset[J]. International Journal of Computer Vision,2019,127(3):302-321. [6] LIU Ze,LIN Yutong,CAO Yue,et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal:IEEE,2021:9992-10002. [7] XIE Enze,WANG Wenhai,YU Zhiding,et al. SegFormer:simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems,2021,34:12077-12090. [8] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas:IEEE,2016:770-778. [9] WOO S,PARK J,LEE J Y,et al. CBAM:convolutional block attention module[C]//Proceedings of 2018 European Conference on Computer Vision (ECCV). Cham:Springer,2018:3-19. [10] HOWARD A,SANDLER M,CHEN Bo,et al. Searching for MobileNetV3[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul:IEEE,2019:1314-1324. [11] NIU Ruigang,SUN Xian,TIAN Yu,et al. Hybrid multiple attention network for semantic segmentation in aerial images[J]. IEEE Transactions on Geoscience and Remote Sensing,2021,60:5603018. [12] HOU Qibin,ZHOU Daquan,FENG Jiashi. Coordinate attention for efficient mobile network design[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville:IEEE,2021:13708-13717. [13] GAO Shanghua,CHENG Mingming,ZHAO Kai,et al. Res2Net:a new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,43(2):652-662. [14] FU Jun,LIU Jing,TIAN Haijie,et al. Dual attention network for scene segmentation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach:IEEE,2019:3141-3149. [15] YUAN Yuhui,CHEN Xilin,WANG Jingdong. Object-contextual representations for semantic segmentation[C]//Proceedings of 2020 European Conference on Computer Vision (ECCV). Cham:Springer,2020:173-190. [16] GENG Z Y,GUO M H,CHEN H X,et al. Is attention better than matrix decomposition[C]//Proceedings of the 9th International Conference on Learning Representations(ICLR). [S. l. ]:Springer,2021.

基于CBAM增强的轻量级遥感影像语义分割方法

A lightweight remote sensing image semantic segmentation method based on CBAM enhancement

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨颜光, 钱建国, 于斌, 郭洁, 焦扬. 轻量的增强型激光雷达-惯性-视觉里程计系统[J]. 测绘通报, 2025, 0(9): 78-83,104.
[2]	江峰, 陈超. 基于深度学习的耕地信息提取与地表变化监测分析[J]. 测绘通报, 2025, 0(9): 131-134.
[3]	邓小龙, 黄志海, 郭波. 改进分割大模型的桥梁缆索损伤语义分割方法[J]. 测绘通报, 2025, 0(9): 112-117.
[4]	汪志刚, 冯凯, 刘懿晨, 刘辉, 张文俊. 融合LightGlue的双目视觉SLAM算法[J]. 测绘通报, 2025, 0(9): 168-172.
[5]	王英谋, 李雷. 基于遥感影像综合生产平台智能协同的DOM生产技术[J]. 测绘通报, 2025, 0(8): 142-148.
[6]	胡耀锋, 程相兵, 陈嘉琦. 城市立体感知网建设关键技术与监测应用——以广州市历史文化街区为例[J]. 测绘通报, 2025, 0(8): 174-178.
[7]	董斯源, 杨元维, 高贤君, 谭美淋, 杜斌, 屈伟军, 陈宁生. 基于贪心算法与空间关系自优化影像数据集高效筛选方法[J]. 测绘通报, 2025, 0(8): 100-106.
[8]	李超, 刘清屹, 张佳伟, 石勇, 杨敏. 基于图像增强和改进RT-DETR的水下垃圾检测算法[J]. 测绘通报, 2025, 0(8): 128-136.
[9]	杜建超, 张雷, 白晋颖, 李婷婷. 基于PIE-Engine的陕西省公路网遥感影像分析[J]. 测绘通报, 2025, 0(7): 46-51.
[10]	张超, 熊春宝, 连思达. 基于深度学习的海洋平台基础环境监测方法[J]. 测绘通报, 2025, 0(6): 12-17.
[11]	闫白羽, 翟国君, 边少锋. 基于白化着色的沉船和失事飞机风格迁移方法[J]. 测绘通报, 2025, 0(6): 73-77.
[12]	陈登峰, 何拓航, 杨小燕, 刘世鹏, 孟屯良. 路基病害雷达图像多视图融合识别方法[J]. 测绘通报, 2025, 0(5): 66-73.
[13]	赵辰瑞, 连增增, 田亚林, 贺刘辉, 陈浩, 王鹏辉, 王孟奇. BiLSTM-Chan算法在超宽带室内定位中的应用[J]. 测绘通报, 2025, 0(5): 100-105.
[14]	李娟, 蔡哲理, 向娟, 袁方芳, 袁光碧, 雷邦俊. 基于中高分辨率遥感影像的植被综合盖度时空演变分析[J]. 测绘通报, 2025, 0(5): 21-26.
[15]	王靖凯, 葛星彤, 李兆博, 丁翔, 彭玲. 基于改进HRNet的高速公路路域内光伏板信息提取[J]. 测绘通报, 2025, 0(5): 74-78,99.