基于双路径编码的遥感建筑物图像分割方法

doi:10.3778/j.issn.1673-9418.2310030

摘要/Abstract

摘要： 高分辨率遥感图像建筑物分割是遥感影像研究的热点之一，而高分辨率遥感图像中建筑物尺度多样容易导致错分割、漏分割和边界模糊。针对上述问题，基于U-Net网络结构提出了一种双路径编码的遥感建筑物图像分割网络（DCU-Net）。DCU-Net在U-Net上加入一条并行编码路径，形成双路径编码结构。在编码阶段设计了密集残差编码模块（DRCM）和多尺度空洞卷积编码模块（MDCCM）以增强多尺度特征提取。在网络中加入双路融合注意力模块（DFAM），增强网络对特征的表达能力。为验证网络有效性，在WHU与Massachusetts数据集上进行实验，召回率、F1分数和交并比指标在WHU上达到91.26%、92.33%和86.15%，在Massachusetts Buildings上达到81.64%、84.33%和82.72%。结果表明，DCU-Net对于不同尺度的建筑物提取有较高的提取精度。

关键词: 遥感影像, 建筑物分割, 双路径编码, 注意力机制, 多尺度特征

Abstract: Building segmentation in high resolution remote sensing images is one of the hotspots in remote sensing image research. The diversity of building scales in high-resolution remote sensing images easily leads to wrong segmentation, missing segmentation and fuzzy boundaries. In order to solve the above problems, this paper proposes a remote sensing building image segmentation network based on U-Net network structure with double coder U-shaped network (DCU-Net). DCU-Net adds a parallel coding path to U-Net to form a dual-path coding structure. Dense residual coding module (DRCM) and multi-scale dilated convolutional coding module (MDCCM) are designed in the encoding stage to enhance multi-scale feature extraction. The dual hybrid attention module (DFAM) is added to the network to enhance the expression ability of the network for features. In order to verify the effectiveness of the network, experiments are carried out on WHU and Massachusetts datasets. The recall, F1 and intersection over union ratio indicators reach 91.26%, 92.33% and 86.15% on WHU dataset, and reach 81.64%, 84.33% and 82.72% on Massachusetts Buildings dataset. The results show that DCU-Net has high extraction accuracy for building extraction at different scales.

Key words: remote sensing image, building segmentation, dual-path coding, attention mechanism, multi-scale feature

苏赋, 李沁, 马傲. 基于双路径编码的遥感建筑物图像分割方法[J]. 计算机科学与探索, 2024, 18(10): 2704-2711.

SU Fu, LI Qin, MA Ao. Dual-Path Coding of Remote Sensing Building Image Segmentation Method[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(10): 2704-2711.

参考文献

[1] 张飞, 邵媛, 黄晖, 等. 近20年城市遥感研究现状及其发展趋势[J]. 生态学报, 2021, 41(8): 3255-3276.
ZHANG F, SHAO Y, HUANG H, et al. Research status and development trend of urban remote sensing in the past 20 years[J]. Acta Ecologica Sinica, 2021, 41(8): 3255-3276.
[2] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2015: 3431-3440.
[3] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Oct 5-9, 2015. Cham: Springer, 2015: 234-241.
[4] BADRINARAYANAN V, KENDALL A, CIPOLLA R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[5] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[EB/OL]. [2023-08-15]. https://arxiv.org/abs/1412.7062.
[6] 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 Tran-sactions on Pattern Analysis and Machine Intelligence, 2017, 40(4): 834-848.
[7] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethin-king atrous convolution for semantic image segmentation[EB/OL]. [2023-08-15]. https://arxiv.org/abs/1706.05587.
[8] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmen-tation[C]//Proceedings of the 15th European Conference on Computer Vision. Cham: Springer, 2018: 801-818.
[9] KAMPFFMEYER M, SALBERG A B, JENSSEN R. Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 1-9.
[10] ZHAO K, KANG J, JUNG J, et al. Building extraction from satellite images using mask R-CNN with building boundary regularization[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Washington:IEEE Computer Society, 2018: 247-251.
[11] YI Y, ZHANG Z, ZHANG W, et al. Semantic segmentation of urban buildings from VHR remote sensing imagery using a deep convolutional neural network[J]. Remote Sensing, 2019, 11(15): 1774.
[12] 张春森, 葛英伟, 蒋萧. 基于稀疏约束SegNet的高分辨率遥感影像建筑物提取[J]. 西安科技大学学报, 2020, 40(3): 441-448.
ZHANG C S, GE Y W, JIANG X. Building extraction from high-resolution remote sensing images based on sparse-constrained SegNet[J]. Journal of Xi’an University of Science and Technology, 2020, 40(3): 441-448.
[13] HE N, FANG L, PLAZA A. Hybrid first and second order attention Unet for building segmentation in remote sensing images[J]. Science China Information Sciences, 2020, 63: 1-12.
[14] GUPTA R, SHAH M. RescueNet: joint building segmentation and damage assessment from satellite imagery[C]//Proceedings of the 2020 25th International Conference on Pattern Recognition. Piscataway: IEEE, 2021: 4405-4411.
[15] ABDOLLAHI A, PRADHAN B, SHUKLA N, et al. Multi-object segmentation in complex urban scenes from highresolution remote sensing data[J]. Remote Sensing, 2021, 13(18): 3710.
[16] PRIYANKA, SRAVYA N, LAL S, et al. DIResUNet: architecture for multiclass semantic segmentation of high resolution remote sensing imagery data[J]. Applied Intelligence, 2022, 52(13): 15462-15482.
[17] ZHOU D, HOU Q, CHEN Y, et al. Rethinking bottleneck structure for efficient mobile network design[C]//Proceedings of the 16th European Conference on Computer Vision, Glasgow, Aug 23-28, 2020. Cham: Springer, 2020: 680-697.
[18] YANG M, YU K, ZHANG C, et al. DenseASPP for semantic segmentation in street scenes[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2018: 3684-3692.
[19] HOU Q, ZHANG L, CHENG M M, et al. Strip Pooling: rethin-king spatial pooling for scene parsing[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 4003-4012.
[20] WANG Q, WU B, ZHU P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceed-ings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11534-11542.
[21] LIN G, MILAN A, SHEN C, et al. RefineNet: multi-path refinement networks for high-resolution semantic segmentation[C]//Proceedings of the 2017 IEEE Conference on Com-puter Vision and Pattern Recognition. Washington: IEEE Computer Society, 2017: 1925-1934.
[22] LI H, QIU K, CHEN L, 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, 2020, 18(5): 905-909.
[23] 明兴涛, 杨德宏. 基于多模块的遥感影像建筑物提取方法[J]. 激光与光电子学进展, 2024, 61(4): 0428004.
MING X T, YANG D H. Building extraction from remote sensing image based on multi-module[J]. Laser & Optoelectronics Progress, 2024, 61(4): 0428004.
[24] 李小祥, 黄亮, 朱娟娟, 等. 边缘增强的EDU-Net遥感影像建筑物提取[J]. 遥感信息, 2023, 38(2): 134-141.
LI X X, HUANG L, ZHU J J, et al. Edeg-enhanced EDU-Net for remote sensing image building extraction[J]. Remote Sensing Information, 2023, 38(2): 134-141.