计算机科学与探索2024，Vol.18Issue(10)：2712-2726,15.DOI:10.3778/j.issn.1673-9418.2310073
融合Partial卷积与残差细化的遥感影像建筑物提取算法
Building Extraction Algorithm for Remote Sensing Images by Fusing Partial Con-volution and Residual Refinement
摘要
Abstract
Due to the high similarity between background and buildings in high spatial resolution remote sensing im-ages,which makes it difficult for the network to take into account buildings of different sizes,the pixels in the building boundary region are confused with the background,and the building boundaries are easily missed.In order to solve the above problems,the building extraction algorithm(UUNet)for remote sensing images fusing partial convolution and residual refinement is proposed.Using U-Net as the baseline network,firstly,this paper improves the encoder.It adds two Conv4×4 at the front end of the encoder to expand the sensing field at the beginning and capture more re-mote sensing image feature information.It utilizes the PC module constructed by partial convolution(PConv3×3)to enhance the ability of the encoder to extract multi-scale building features,and downsamples twice with Conv2×2 to reduce the loss of building feature information.Secondly,this paper reduces the number of parameters.It crops the three-layer structure of the U-Net network decoder to a UUNet network decoder.Lastly,it adds an improved residual refinement module.It constructs a U-shaped residual refinement module cropped to a three-layer structure at the out-put of the decoder,to further purify the rough building feature maps output from the decoder,so as to make the edge information of the buildings clearer.Decoder is jump-connected to the encoder of the U-shaped residual refinement module to preserve the initial features,and SimAM is embedded in the refinement module to improve the building focus,optimize the network to improve the boundary blurring,and enhance the quality of target boundary extrac-tion.In the ablation experiment conducted on the Satellite dataset Ⅱ(East Asia),UUNet shows improvements over U-Net,with IoUBuilding,IoUBackground,F1,OA and mIoU increased by 2.78 percentage points,0.12 percentage points,1.91 percentage points,0.19 percentage points and 1.45 percentage points,respectively,indicating that UUNet out-performs the baseline network.Furthermore,comparative experiments on both Satellite dataset Ⅱ(East Asia)and WHU dataset demonstrate that UUNet performs better than existing mainstream algorithms,significantly enhancing building extraction in high-resolution remote sensing images.关键词
高分辨率遥感影像/建筑物提取/边界平滑/多尺度特征/U-Net/Partial卷积Key words
high resolution remote sensing imagery/building extraction/boundary smoothing/multiscale features/U-Net/Partial convolution分类
信息技术与安全科学引用本文复制引用
侯佳兴,齐向明,郝明,张进..融合Partial卷积与残差细化的遥感影像建筑物提取算法[J].计算机科学与探索,2024,18(10):2712-2726,15.基金项目
国家自然科学基金面上项目(62173171).This work was supported by the National Natural Science Foundation of China(62173171). （62173171）
