融合YOLO与CBAM模型的建筑物轮廓遥感提取方法

doi:10.13474/j.cnki.11-2246.2026.0720

测绘通报 ›› 2026, Vol. 0 ›› Issue (7): 136-141.doi: 10.13474/j.cnki.11-2246.2026.0720

融合YOLO与CBAM模型的建筑物轮廓遥感提取方法

毛亚琴^1,2, 丁小辉³, 涂梨平¹, 范军林^1,2, 何雨玥³, 徐荣华⁴

1. 江西省核工业地质调查院, 江西南昌 330038;
2. 江西核工业测绘院集团有限公司, 江西南昌 330038;
3. 江西财经大学, 江西南昌 330013;
4. 江西省地质调查勘查院关键矿产资源勘查与开发江西省重点实验室, 江西南昌 330009

收稿日期:2025-11-05 发布日期:2026-08-15
作者简介:毛亚琴(1992—),女,主要研究方向为遥感测绘、三维建模。E-mail:lemonmyq0805@163.com
基金资助:
国家自然科学基金(42201467);江西省地质局青年科学技术带头人培养计划(2025JXDZKJRC06)

A remote sensing extraction method for building contours based on YOLO and CBAM model fusion

Mao Yaqin^1,2, Ding Xiaohui³, Tu Liping¹, Fan Junlin^1,2, He Yuyue³, Xu Ronghua⁴

1. Jiangxi Provincial Institute of Nuclear Geological Survey, Nanchang 330038, China;
2. Jiangxi Nuclear Industry Surveying and Mapping Institute Group Co., Ltd., Nanchang 330038, China;
3. Jiangxi University of Finance and Economics, Nanchang 330013, China;
4. Jiangxi Geological Survey and Exploration Institute(Jiangxi Province Key Laboratory of Exploration and Development of Critical Mineral Resources), Nanchang 330009, China

Received:2025-11-05 Published:2026-08-15

摘要/Abstract

摘要： [目的] 建筑物轮廓遥感提取是自然资源调查与空间规划的重要基础。针对基于遥感的建筑物轮廓提取面临的因建筑物轮廓几何特征复杂而引起的提取精度低等问题,本文提出了融合YOLO11模型与卷积块注意力模块(CBAM)的YOLO-CBAM模型,用于建筑物轮廓遥感提取。[方法] 模型采用公开的GF-7建筑物数据集进行训练与测试,并与YOLOv8、YOLO11、融合YOLO11与CA(coordinate attention)注意力机制的YOLO-CA模型、U-Net、DeepLabV3及Mask-RCNN模型进行了比较。[结果] 试验结果显示,YOLO-CBAM模型的IoU、Dice指数、mAP@0.5值、F₁值及最大召回率(R)分别为71.1%、81.5%、74.7%、0.72及88.0%。[结论] 这些评价指标的值均优于YOLOv8、YOLO11及YOLO-CA模型,表明CBAM的引入可以有效提升YOLO11模型对遥感建筑物轮廓提取的精度。

关键词: YOLO模型, 建筑物轮廓, 高分遥感, 注意力机制

Abstract: [Purposes] Remote sensing extraction of building outlines serves as a vital source of foundational data for natural resource surveys and spatial planning.Addressing the challenge of low extraction accuracy,stemming from the complex geometric characteristics of building contours in remote sensing imagery,this study proposes the YOLO-CBAM model,which integrates the YOLO11 framework with the convolutional block attention module (CBAM)for enhanced remote sensing building contour extraction. [Methods] The model is trained and validated using the public GF-7 building dataset and compared against YOLOv8,YOLO11,the YOLO-CA model (incorporating the Coordinate Attention mechanism with YOLO11),U-Net,DeepLabV3,and Mask-RCNN. [Findings] Experimental results demonstrate that the YOLO-CBAM model achieves IoU,Dice index,mAP@0.5,F₁ score,maximum recall(R) values of 71.1%,81.5%,74.7%,0.72,88.0%,respectively. [Conclusions] These evaluation metrics outperform those of YOLOv8,YOLO11,YOLO-CA,U-Net,DeepLabV3,and Mask-RCNN confirming that the integration of CBAM significantly improves the accuracy of YOLO11 in remote sensing-based building contour extraction.

Key words: YOLO model, building contours, high-resolution remote sensing, attention mechanism

中图分类号:

P237

毛亚琴, 丁小辉, 涂梨平, 范军林, 何雨玥, 徐荣华. 融合YOLO与CBAM模型的建筑物轮廓遥感提取方法[J]. 测绘通报, 2026, 0(7): 136-141.

Mao Yaqin, Ding Xiaohui, Tu Liping, Fan Junlin, He Yuyue, Xu Ronghua. A remote sensing extraction method for building contours based on YOLO and CBAM model fusion[J]. Bulletin of Surveying and Mapping, 2026, 0(7): 136-141.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://tb.chinasmp.com/CN/10.13474/j.cnki.11-2246.2026.0720

http://tb.chinasmp.com/CN/Y2026/V0/I7/136

参考文献

[1] 殷吉崇,武芳,翟仁健,等.面向建筑物轮廓规则化的双路径边界约束与相对论生成对抗网络[J].测绘学报,2024,53(7):1444-1457.
[2] 陈胜鹏,卢浩,陈晓凤,等.端到端的遥感图像建筑物矢量轮廓提取方法[J/OL].测绘地理信息,1-10[2026-04-10].https://doi.org/10.14188/j.2095-6045.20240670.
[3] 张维,赵亮.激光技术和遥感信息相融合的建筑物轮廓识别研究[J].激光杂志,2020,41(11):100-104.
[4] Zhang Tao,Wei Shiqing,Zhou Yikang,et al.P2PFormer:a primitive-to-polygon method for regular building contour extraction from remote sensing images[J].IEEE Transactions on Geoscience and Remote Sensing,2024,62:4414012.
[5] Wu Guangming,Guo Zhiling,Shi Xiaodan,et al.A boundary regulated network for accurate roof segmentation and outline extraction[J].Remote Sensing,2018,10(8):1195.
[6] Chen Shanxiong,Shi Wenzhong,Zhou Mingting,et al.CGSANet:a contour-guided and local structure-aware encoder-decoder network for accurate building extraction from very high-resolution remote sensing imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:1526-1542.
[7] Zhang Lisa,Bai Min,Liao Renjie,et al.Learning deep structured active contours end-to-end[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:8877-8885.
[8] Cheng D,Liao Renjie,Fidler S,et al.DARNet:deep active ray network for building segmentation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach:IEEE,2020:7423-7431.
[9] Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston:IEEE,2015:3431-3440.
[10] Wei Shiqing,Ji Shunping,Lu Meng.Toward automatic building footprint delineation from aerial images using CNN and regularization[J].IEEE Transactions on Geoscience and Remote Sensing,2020,58(3):2178-2189.
[11] Girard N,Smirnov D,Solomon J,et al.Polygonal building extraction by frame field learning[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville:IEEE,2021:5887-5896.
[12] Badrinarayanan V,Kendall A,Cipolla R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[EB/OL].[2025-10-20].https://ieeexplore.ieee.org/document/7803544.
[13] Ronneberger O,Fischer P,Brox T.U-Net:convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.Cham:Springer International Publishing,2015:234-241.
[14] Chen L C,Zhu Yukun,Papandreou G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Computer Vision-ECCV 2018.Cham:Springer International Publishing,2018:833-851.
[15] Chen L C,Papandreou G,Kokkinos I,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
[16] 王朝洋,苏一少,骆剑承,等.融合道路邻近关系的高分遥感目标分割方法[J].测绘学报,2025,54(7):1294-1304.
[17] 王德文,宋学帅,李成浩,等.基于边缘增强和多尺度特征融合的遥感图像船舰检测[J].智能系统学报,2026,21(1):60-71.
[18] Song Ziyu,Wang Weixi,Hao Zhenyu,et al.Building footprint extraction from aerial images using an edge-aware YOLO-v8 network[J].The International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2024,XLVIII-1-2024:605-611.
[19] 汤莉,张健宇,姚睿.基于改进YOLOv11的雾天目标检测算法[J/OL].计算机应用,1-12[2025-10-11].https://www.joca.cn/CN/10.11772/j.issn.1001-9081.2025070921.
[20] Liu Haoliang,Xiong Wei,Zhang Yu.YOLO-CORE:contour regression for efficient instance segmentation[J].Machine Intelligence Research,2023,20(5):716-728.
[21] Cao M T.Drone-assisted segmentation of tile peeling on building façades using a deep learning model[J].Journal of Building Engineering,2023,80:108063.
[22] Zeng Shuang,Yang Wenzhu,Jiao Yanyan,et al.SCA-YOLO:a new small object detection model for UAV images[J].The Visual Computer,2024,40(3):1787-1803.
[23] Gao Jinfeng,Chen Yu,Wei Yongming,et al.Detection of specific building in remote sensing images using a novel YOLO-S-CIOU model.case:gas station identification[J].Sensors,2021,21(4):1375.
[24] Chen Peimin,Huang Huabing,Ye Feng,et al.A benchmark GaoFen-7 dataset for building extraction from satellite images[J].Scientific Data,2024,11:187.

融合YOLO与CBAM模型的建筑物轮廓遥感提取方法

A remote sensing extraction method for building contours based on YOLO and CBAM model fusion

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]	李宇程, 纪硕磊, 陈海林, 黄恒英. 基于改进U-Net的电晕放电紫外图像检测与分割算法[J]. 测绘通报, 2026, 0(6): 157-163.
[2]	李宏强, 杨魁, 车国伟. 融合注意力机制的加权ResNet在SAR洪水淹没区提取中的应用[J]. 测绘通报, 2026, 0(4): 134-139.
[3]	张睿哲, 赵留学, 周恺, 赖曦文, 张佩. 多层次注意力驱动的Mamba输电走廊建筑变化检测[J]. 测绘通报, 2026, 0(4): 140-146.
[4]	滕敏, 张博, 徐佳伟, 林聪, 沈雨, 储征伟. 基于改进YOLOv8s的无人机影像车辆目标检测算法[J]. 测绘通报, 2026, 0(2): 68-73,80.
[5]	纪硕磊, 黄恒英, 李宇程, 陈海林. 基于多尺度特征融合的无人机紫外成像220 kV高压设备局部放电检测[J]. 测绘通报, 2026, 0(2): 161-167.
[6]	陈楠, 张标, 杨楠, 刘洲洲. 双层耦合非参数Bayesian的遥感图像时空反射率融合[J]. 测绘通报, 2025, 0(9): 45-50.
[7]	王立志, 肖东升. IVYA-SIAM联合优化的多模态人口空间化模型构建及驱动效应分析[J]. 测绘通报, 2025, 0(8): 95-99,106.
[8]	殷俊婕, 关戴婉静, 李浩, 张晓阳, 马于杰, 邢汉发. 面向海岸线排污口的无人机目标识别数据集[J]. 测绘通报, 2025, 0(8): 112-117.
[9]	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.
[10]	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.
[11]	孙凯, 徐青, 张瑞鑫, 苏友能. 改进特征金字塔池化的遥感影像障碍物提取[J]. 测绘通报, 2025, 0(4): 90-95.
[12]	李建, 王健, 王雷, 李敏, 杨立克, 赵艺龙. 双重注意力机制的电力走廊点云语义分割[J]. 测绘通报, 2025, 0(4): 127-133.
[13]	谢巴图, 胡佳睿, 潘俊. 基于双路全局信息优化网络的遥感影像海陆分割算法[J]. 测绘通报, 2025, 0(3): 52-58,86.
[14]	赵兴旺, 赵妍, 刘超, 刘春阳. 基于改进的DeepLabV3+网络的Sentinel-1影像水体提取[J]. 测绘通报, 2025, 0(3): 66-70.
[15]	刘晓栋, 赵晨萌, 任迎华, 杨礼平, 赵立科, 张卡. 面向无人机与遥感影像的烟雾火焰目标提取方法[J]. 测绘通报, 2025, 0(12): 7-14.