基于多尺度与双注意力网络的城市边缘区不透水面变化检测  

Impervious Surface Change Detection in Urban Fringe Areas Based on Multi-scale and Dual-attention Network

作　　者：穆正阳 戴建国[1,2] 张国顺 侯文庆[3] 陈沛沛 曹宇娟 许淼淼 MU Zhengyang;DAI Jianguo;ZHANG Guoshun;HOU Wenqing;CHEN Peipei;CAO Yujuan;XU Miaomiao(College of Information Science&Technology,Shihezi University,Shihezi,Xinjiang 832000,China;Geospatial Information Engineering Research Center,Xinjiang Production and Construction Corps,Shihezi,Xinjiang 832000,China;School of Information Network Security,Xinjiang University of Political and Law,Tumxuk,Xinjiang 843900,China)

机构地区：[1]石河子大学信息科学与技术学院,新疆石河子832000 [2]新疆生产建设兵团兵团空间信息工程技术研究中心,新疆石河子832000 [3]新疆政法学院信息网络安全学院,新疆图木舒克843900

出　　处：《计算机科学》2024年第S02期355-362,共8页Computer Science

基　　金：国家自然科学基金(32260388)。

摘　　要：不透水面作为城市化的重要特征,可直观反映城市化范围,利用遥感影像与计算机视觉检测不同时序间城市边缘区不透水面的变化,是观测城市扩张的有效手段,对于城建规划和城市可持续发展具有重要意义。然而,城市边缘区作为城市和自然环境的过渡区域,地物类型复杂凌乱,具有高度异质性,为变化检测任务带来了巨大挑战。为解决这些问题,该方法采用SE(Squeeze and Excitation)压缩激励结构与多尺度融合模块(Multi-scale Fusion Module,MSFM)对Deeplabv3+网络进行改进优化,构建高精度不透水面变化提取网络MSDANet(Muti-scale Dual-attention Network,MSDANet),实现不透水面变化自动提取。同时,基于Google Earth卫星影像平台,获取2017年与2021年乌鲁木齐城市边缘区可见光影像,构建一个注释良好的高分辨率不透水面变化检测数据集HISCD,并将其开源。通过与7种主流变化检测网络进行对比,MSDANet取得了最好的结果,具有良好的变化提取能力,能够精准提取多种不透水面变化类型。在HISCD测试集中OA,Precision,Recall,F1与MIoU各指标分别达到了90.77%,80.51%,78.83%,79.63%与68.80%。该方法为城市扩张分析提供了一种新颖的方法,为城市空间规划提供了有效的技术支持。As an important feature of urbanization,impervious surface can intuitively reflect the scope of urbanization,and the use of remote sensing imagery and computer vision to detect the change of impervious surface in urban fringe areas between different time series is an effective means of observing the expansion of the city,which is of great significance to the urban construction planning and sustainable development of the city.Nevertheless,the peri-urban regions situated between urban and natural environments,are characterized by intricate and haphazard characteristics,exhibiting a high degree of heterogeneity.Consequently,this presents a formidable challenge when undertaking the task of detecting changes.To solve these problems,this paper adopts a SE compression excitement structure and multi-scale fusion module(MSFM)to improve and optimize the Deeplabv3+network,and constructs a high-precision impervious surface change extraction model,MSDANet,to realize the automatic extraction of impervious surface change.Meanwhile,based on the Google Earth satellite imagery platform,high-resolution images of Urumqi’s metropolitan outskirts in 2017 and 2021 are procured,and a well-annotated high-resolution impervious surface alteration detection(HISCD)dataset is established and made publicly available.By comparing with leading change detection networks,MSDANet achieves the best outcomes with good change extraction capability,and is able to accurately extract multiple impervious surface change types.The metrics of OA,Precision,Recall,F1 and MIoU in the HISCD test set reaches 90.77%,80.51%,78.83%,79.63%and 68.80%,respectively.This investigation provides a novel approach for evaluation urban spread analysis and effective technical support for urban spatial planning.

关 键 词：城市边缘区 城市扩张 不透水面 变化检测 高分辨率 变化检测数据集 

分 类 号：P231[天文地球—摄影测量与遥感]