液晶与显示2025，Vol.40Issue(9)：1333-1346,14.DOI:10.37188/CJLCD.2025-0108
集成小波变换与全局感知的轻量建筑提取网络
Lightweight building extraction network integrating wavelet transform and global awareness
摘要
Abstract
Building extraction based on deep learning is an important research direction in the field of remote sensing.To effectively balance computational efficiency and extraction accuracy,a lightweight building extraction network integrating wavelet transform and global awareness is proposed.First,by integrating parameter sharing,star-shaped operations,and depthwise separable convolution,a star-shared depthwise convolution block is proposed to efficiently and accurately extract building features.Secondly,wavelet transform and frequency-domain spatial attention are introduced to propose an efficient boundary enhancement module that enhances the network's ability to characterize building boundary features.Finally,employing a lightweight non-local attention mechanism and a hierarchical feature interaction strategy,a global context-aware module is proposed.This module significantly improves the fusion effectiveness of hierarchical features and enhances the overall perception capability during the network's decoding stage.Experimental results demonstrate that the proposed network achieves Intersection over Union(IoU)scores of 90.08%and 79.16%on the publicly available WHU and Inria building extraction datasets,respectively.Concurrently,the model maintains a low parameter count(Params)of 3.09 million,FLOPs of 4.93 billion,and an inference speed of 30.24 frames per second(FPS).Compared to existing methods such as Swin Transformer,BuildFormer,SDSCUNet,EasyNet,HDNet,and CaSaFormerNet,the proposed method achieves higher extraction accuracy while maintaining low computational complexity,achieving a superior balance between computational efficiency and extraction accuracy.关键词
建筑物提取/轻量级/边界增强/小波变换/全局上下文Key words
building extraction/lightweight/boundary enhancement/wavelet transform/global context分类
信息技术与安全科学引用本文复制引用
邵文,邵攀,宋宝贵,熊彪..集成小波变换与全局感知的轻量建筑提取网络[J].液晶与显示,2025,40(9):1333-1346,14.基金项目
国家自然科学基金(No.41901341) （No.41901341）
湖北省自然科学基金(No.2024AFB867) （No.2024AFB867）
湖北省自然科学基金青年基金(No.2024AFB217) （No.2024AFB217）
自然资源部地理国情监测重点实验室开放基金(No.2025NGCM03) Supported by National Natural Science Foundation of China(No.41901341) （No.2025NGCM03）
Natural Science Foundation of Hubei Province(No.024AFB867) （No.024AFB867）
Youth Fund of Hubei Provincial Natural Science Foundation(No.2024AFB217) （No.2024AFB217）
Open Fund for Key Laboratory of Geographic State Monitoring of Ministry of Natural Resources(No.2025NGCM03) （No.2025NGCM03）
