基于双路全局信息优化网络的遥感影像海陆分割算法

doi:10.13474/j.cnki.11-2246.2025.0309

摘要/Abstract

摘要： 针对高分辨率遥感影像中靠岸地物对海陆边界精细化分割的影响,本文提出了一种基于双路全局信息优化网络(DGIONet)的遥感影像海陆分割算法。在编码端,该网络设计基于矩形条带卷积的多尺度空间注意力特征提取模块,利用不同尺度下垂直构建的矩形条带卷积实现多尺度大内核卷积效果,依靠提取到的多尺度特征与模块内的点卷积实现空间注意力机制,从而有效提高网络关注海陆大尺度特征的能力,实现海陆全局信息及上下文信息的特征提取。在解码端,该网络设计双路全局信息优化解码器,解码器内依靠深度可分离空洞卷积信息优化模块和Hamburger全局特征恢复模块,分别利用提取到的全局信息及上下文信息实现特征恢复,同时将编码端提取到的阶段特征与阶段恢复特征融合,以实现更好的信息优化。为验证本文方法的有效性,构建分辨率优于0.3 m的高分辨率遥感影像海陆分割数据集,在此数据集基础上进行对比试验。结果表明,相较于目前主流语义分割方法Vision Transformer,本文方法像素精度提高了3.01%,平均交并比提高了10.51%,即在高分辨率遥感影像的精细化海陆分割问题中具有优势。

关键词: 高分辨率遥感影像, 海陆分割, 深度学习, 卷积神经网络, 注意力机制

Abstract: Addressing the impact of coastal features on the refined segmentation of land-sea boundaries in high-resolution remote sensing images, this paper proposes a land-sea segmentation algorithm for remote sensing images based on DGIONet. In the encoding stage, the network is designed with a multi-scale spatial attention feature extraction module based on rectangular strip convolution, which utilizes rectangular strip convolutions constructed vertically at different scales to achieve a multi-scale large kernel convolution effect. Relying on the extracted multi-scale features and point convolutions within the module, it implements a spatial attention mechanism, effectively enhancing the network's ability to focus on large scale land-sea features, and enabling feature extraction of land-sea global information and contextual information. In the decoding stage, the network incorporates a dual-path global information optimization decoder. Within the decoder, it relies on a depthwise separable dilated convolution information optimization module and a “Hamburger” global feature restoration module to leverage the extracted global and contextual information for feature restoration. Meanwhile, it fuses the stage features extracted from the encoding stage with the stage-restored features to achieve better information optimization. To verify the effectiveness of the proposed method, this paper constructs a high-resolution remote sensing image land-sea segmentation dataset with a resolution better than 0.3m. Comparative experiments conducted on this dataset demonstrate that the proposed method improves pixel accuracy by 3.01% and mean intersection over union(mIoU) by 10.51% compared to the current mainstream semantic segmentation method, Vision Transformer. This proves the advantages of the proposed method in the refined land-sea segmentation of high-resolution remote sensing images.

Key words: high-resolution remote sensing images, sea-land segmentation, deep learning, convolutional neural network, attention mechanism

中图分类号:

P237

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.

XIE Batu, HU Jiarui, PAN Jun. DGIONet:dual-path global information optimization network for sea-land segmentation with remote sensing images[J]. Bulletin of Surveying and Mapping, 2025, 0(3): 52-58,86.

参考文献

[1] 刘万涛,聂云峰,陈兴峰,等. 复杂背景下深度学习方法的夜光船舶目标检测[J]. 航天返回与遥感,2022,43(3):124-137.
[2] 吴一全,刘忠林. 遥感影像的海岸线自动提取方法研究进展[J]. 遥感学报,2019,23(4):582-602.
[3] CAO Ran,FANG Leyuan,LU Ting,et al. Self-attention-based deep feature fusion for remote sensing scene classification[J]. IEEE Geoscience and Remote Sensing Letters,2021,18(1):43-47.
[4] 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.
[5] AGHDAMI-NIA M,SHAH-HOSSEINI R,ROSTAMI A,et al. Automatic coastline extraction through enhanced sea-land segmentation by modifying standard U-Net[J]. International Journal of Applied Earth Observation and Geoinformation,2022,109:102785.
[6] CUI Binge,JING Wei,HUANG Ling,et al. SANet:a sea-land segmentation network via adaptive multiscale feature learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,14:116-126.
[7] CHEN Yujia,ZHANG Guo,CUI Hao,et al. A novel weakly supervised semantic segmentation framework to improve the resolution of land cover product[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2023,196:73-92.
[8] ZHAO Wencheng,XU Xianze,ZHU Yanyan,et al. Active contour model based on local and global Gaussian fitting energy for medical image segmentation[J]. Optik,2018,158:1160-1169.
[9] HE Xin,ZHOU Yong,ZHAO Jiaqi,et al. Swin transformer embedding U-Net for remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing,2022,60:4408715.
[10] 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.
[11] LI Haifeng,QIU Kaijian,CHEN Li,et al. SCAttNet:semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters,2021,18(5):905-909.
[12] 高慧,阎晓东,张衡,等. 基于Res2Net的多尺度遥感影像海陆分割方法[J]. 光学学报,2022,42(18):147-154.
[13] GUO Menghao,LU Chengze,LIU Zhengning,et al. Visual attention network[J]. Computational Visual Media,2023,9(4):733-752.
[14] GUO Menghao,XU Tianxing,LIU Jiangjiang,et al. Attention mechanisms in computer vision:a survey[J]. Computational Visual Media,2022,8(3):331-368.
[15] GENG Zhengyang,GUO Menghao,CHEN Hongxu,et al. Is attention better than matrix decomposition？[EB/OL].[2024-06-07].https://blog.csdn.net/qq.45041871/article/details/127773250.
[16] XIONG Xuan,WANG Xiaopeng,ZHANG Jiahua,et al. TCUNet:a lightweight dual-branch parallel network for sea-land segmentation in remote sensing images[J]. Remote Sensing,2023,15(18):4413.
[17] RONNEBERGER O,FISCHER P,BROX T. U-Net:convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention. Cham:Springer International Publishing,2015:234-241.
[18] CHEN L C,PAPANDREOU G,SCHROFF F,et al. Rethinking atrous convolution for semantic segmentation image segmentation[EB/OL]. [2017-12-05].https://arxiv.org/abs/1706.05587v2.
[19] ZHAO Hengshuang,SHI Jianping,QI Xiaojuan,et al. Pyramid scene parsing network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:6230-6239.
[20] YUAN Yuhui,CHEN Xilin,WANG Jingdong. Object-contextual representations for semantic segmentation[M]//Computer Vision - ECCV 2020. Cham:Springer International Publishing,2020:173-190.
[21] XU Jiacong,XIONG Zixiang,BHATTACHARYYA S P. PIDNet:a real-time semantic segmentation network inspired by PID controllers[C]//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver:IEEE,2023:19529-19539.