Journal of Frontiers of Computer Science and Technology ›› 2024, Vol. 18 ›› Issue (10): 2704-2711.DOI: 10.3778/j.issn.1673-9418.2310030

• Graphics·Image • Previous Articles     Next Articles

Dual-Path Coding of Remote Sensing Building Image Segmentation Method

SU Fu, LI Qin, MA Ao   

  1. School of Electrical Engineering and Information, Southwest Petroleum University, Chengdu 610500, China
  • Online:2024-10-01 Published:2024-09-29

基于双路径编码的遥感建筑物图像分割方法

苏赋,李沁,马傲   

  1. 西南石油大学 电气信息学院,成都 610500

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

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