光学精密工程2023，Vol.31Issue(22)：3371-3382,12.DOI:10.37188/OPE.20233122.3371
面向遥感建筑物提取的轻型多尺度差异网络
Lightweight multi-scale difference network for remote sensing building extraction
摘要
Abstract
To address the problem of low accuracy of building extraction in high-resolution remote sensing images due to the diverse shapes and sizes of buildings and large number of parameters in traditional seg-mentation models,a Lightweight Multi-scale Difference network(LMD-Net)based on encoding-decod-ing is proposed.First,to avoid the invalid parameters caused by the degraded model performance due to the stacking of single feature processing units,a lightweight differential model is designed to improve the performance by integrating the functional differences of codec structures.Next,a Multi-scale Dilation Per-ception(MSDP)module is introduced to enhance the ability of the network to capture multi-scale target features.Finally,the double fusion mechanism is used to effectively aggregate the feature information of the deep jump connection and deep decoder to enhance the feature recovery ability of the decoder.To veri-fy the validity and applicability of LMD-Net,the open source WHU building dataset was used as the data source to evaluate the accuracy and efficiency of LMD-Net and the common semantic segmentation net-work as well as the results from recent relevant literature.The results show that LMD-Net has obvious ad-vantages in both efficiency and accuracy,which not only greatly reduces the parameter number and calcula-tion amount of the model but also improves the intersection ratio and accuracy by 3.23%and 2.57%,re-spectively.Consequently,this model is advantageous in the field of building extraction based on high-reso-lution remote sensing images to generate an urban spatial information base.关键词
高分辨率遥感影像/多尺度/建筑物提取/编码-解码/轻型Key words
high resolution remote sensing image/multi-scale/building extraction/coding-decoding/light weight分类
天文与地球科学引用本文复制引用
李国燕,武海苗,董春华,刘毅..面向遥感建筑物提取的轻型多尺度差异网络[J].光学精密工程,2023,31(22):3371-3382,12.基金项目
国家自然科学基金资助项目(No.52178295) （No.52178295）
