计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231200064-8.doi: 10.11896/jsjkx.231200064

• 图像处理&多媒体技术 • 上一篇    下一篇

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

穆正阳1,2, 戴建国1,2, 张国顺1,2, 侯文庆3, 陈沛沛1,2, 曹宇娟1,2, 许淼淼1,2   

  1. 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
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 戴建国(daijianguo2002@sina.com)
  • 作者简介:(xinxinmuxr@163.com)
  • 基金资助:
    国家自然科学基金(32260388)

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

MU Zhengyang1,2, DAI Jianguo1,2, ZHANG Guoshun1,2, HOU Wenqing3, CHEN Peipei1,2, CAO Yujuan1,2, XU Miaomiao1,2   

  1. 1 College of Information Science & Technology,Shihezi University,Shihezi,Xinjiang 832000,China
    2 Geospatial Information Engineering Research Center,Xinjiang Production and Construction Corps,Shihezi,Xinjiang 832000,China
    3 School of Information Network Security,Xinjiang University of Political and Law,Tumxuk,Xinjiang 843900,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:MU Zhengyang,born in 1999,postgra-duate.His main research interests include remote sensing applications and image processing
    DAI Jianguo,born in 1975,Ph.D,profe-ssor.His main research interests include agricultural engineering and biomedical engineering.
  • Supported by:
    National Natural Science Foundation of China(32260388).

PDF (PC)

204

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。

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

Abstract: 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.

Key words: Urban fringe areas, Urban expansion, Impervious surface, Change detection, High-resolution, Change detection dataset

中图分类号: 

  • P231
[1]WANG Z,FU H,LIU H,et al.Urban development sustainability,industrial structure adjustment,and land use efficiency in China[J].Sustainable Cities and Society,2023,89:104338.
[2]CHAO Z,SHANG Z,FEI C,et al.Spatiotemporal Analysis ofUrban Expansion in the Mountainous Hindu Kush Himalayas Region[J].Land,2023,12(3):576.
[3]WANG S,PU Y,LI S,et al.Exploring the Urban Growth Patterns Using Long-time Series Impervious Surface Dataset in the Qinhuai River Basin[J].Remote Sensing Technology and Application,2022,37(3):739-750.
[4]OGRA A,ONATU G.Metropolitan housing development in urban fringe areas-a case study of three metropolitan cities of South Africa:Johannesburg,Ekurhuleni and Tshwane[J].Journal of Civil Engineering and Architecture,2024,18:244-253.
[5]MI J,ZHANG X,LIU L.The analysis on the evolution of temporal and spatial characteristics of impervious surface in Shanghai from 1985 to 2020[J].Remote Sensing Technology and Application,2023,38(2):297-307.
[6]JIAN P,YANXU L,HONG S,et al.Using impervious surfaces to detect urban expansion in Beijing of China in 2000s[J].Chinese Geographical Science 2016,26:229-243.
[7]LI W.Improving Urban Impervious Surfaces Mapping through Integrating Statistical Methods and Spectral Mixture Analysis[J].Remote Sensing,2021,13:2474.
[8]WANG Y,LI M.Urban impervious surface automatic threshold detection model derived from multitemporal Landsat images[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-21.
[9]XU D,WU Y.FE-YOLO:A feature enhancement network for remote sensing target detection[J].Remote Sensing,2021,13:1311.
[10]YE M,RUIWEN N,CHANG Z,et al.A lightweight model of VGG-16 for remote sensing image classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2021,14:6916-6922.
[11] CHEN L,ZHANG H,SONG Y.Extraction of Impervious Surface from High‐Resolution Remote Sensing Images Based on a Lightweight Convolutional Neural Network[J].Wireless Communications and Mobile Computing,2022,2022(1):8636973.
[12]WANG L X,JIA J.Extraction Method of Island buildings in Remote Sensing Images Based on Improved DeepLabv3plus Algorithm[J].Tropical Geography,2021,41(4):834-844.
[13]WANG L,JIA J.Extraction Method of Island buildings in Remote Sensing Images Based on Improved DeepLabv3plus Algorithm.Tropical Geography,2021,41(4):834-844.
[14]DAUDT R C,LE SAUX B,BOULCH A.Fully convolutional siamese networks for change detection[C]//Proceedings of the 2018 25th IEEE International Conference on Image Processing(ICIP).IEEE,2018:4063-4067.
[15]YU X,FAN J,CHEN J,et al.NestNet:A multiscale convolutional neural network for remote sensing image change detection[J].International Journal of Remote Sensing,2021,42(13):4898-4921.
[16]LIU Y,PANG C,ZHANG Z,et al.Building change detection for remote sensing images using a dual-task constrained deep siamese convolutional network model[J].IEEE Geoscience and Remote Sensing Letters,2020,18:811-815.
[17]ZHU C H,CHEN X H,CHEN J,et al.A siamese Nested-UNet for change detection in posterior probability space(SNU-PS)[J].National Remote Sensing Bulletin,2023,27(9):2006-2023.
[18]YANG S,DOU S,LI C.Land-use conflict identification in urbanfringe areas using the theory of leading functional space partition[J].The Social Science Journal,2023,60(4):715-730.
[19]CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:801-818.
[20]LIU Y,PANG C,ZHAN Z,et al.Building change detection for remote sensing images using a dual-task constrained deep siamese convolutional network model[J].IEEE Geoscience and Remote Sensing Letters,2020,18(5):811-815.
[21]CHEN H,QI Z,SHI Z.Remote sensing image change detection with transformers[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-14.
[22]BANDARA W G C,PATEL V M.A transformer-based siamese network for change detection[C]//2022 IEEE International Geoscience and Remote Sensing Symposium(IGARSS 2022).IEEE,2022:207-210.
[23]CHEN H,SHI Z.A spatial-temporal attention-based methodand a new dataset for remote sensing image change detection[J].Remote Sensing,2020,12(10):1662.
[24]JI S,WEI S,LU M.Fully convolutional networks for multi-source building extraction from an open aerial and satellite imagery data set[J].IEEE Transactions on Geoscience and Remote Sensing,2018,57(1):574-586.
[25]PENG D,BRUZZONE L,ZHANG Y,et al.SemiCDNet:Asemisupervised convolutional neural network for change detection in high resolution remote-sensing images[J].IEEE Transactions on Geoscience and Remote Sensing,2020,59(7):5891-5906.
[26]DAUDT R C,LE SAUX B,BOULCH A,et al.Urban change detection for multispectral earth observation using convolutional neural networks[C]//2018 IEEE International Geoscience and Remote Sensing Symposium(IGARSS 2018).IEEE,2018:2115-2118.
[27]ZHANG C,YUE P,TAPETE D,et al.A deeply supervised image fusion network for change detection in high resolution bitemporal remote sensing images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,166:183-200.
[28]LI Z,DONG J.A framework integrating deeplabV3+,transfer learning,active learning,and incremental learning for mapping building footprints[J].Remote Sensing,2022,14(19):4738.
[29]CAI M,YI X,WANG G,et al.Image segmentation method for sweetgum leaf spots based on an improved DeeplabV3+network[J].Forests,2022,13(12):2095.
[30]YANG S,LUO L,LI Q,et al.Auto-identification of linear archaeological traces of the Great Wall in northwest China using improved DeepLabv3+ from very high-resolution aerial imagery[J].International Journal of Applied Earth Observation and Geoinformation,2022,113:102995.
[31]ZHANG C,LI M,WEI D,et al.Enhanced deeplabv3+ for urban land use classification based on uav-borne images[C]//7th International Conference on Image,Vision and Computing(ICIVC 2022).IEEE,2022:449-454.
[32]LU J,ZHOU B,WANG B,et al.Land cover classification of remote sensing images based on improved DeeplabV3+ network[C]//Journal of Physics:Conference Series.IOP Publishing,2022,2400(1):012035.
[33]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[34]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognitin.2018:7132-714.
[35]PAPADOMANOLAKI M,VERMA S,VAKALOPOULOU M,et al.Detecting urban changes with recurrent neural networks from multitemporal Sentinel-2 data[C]//IEEE International Geoscience and Remote Sensing Symposium(IGARSS 2019).IEEE,2019:214-217.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发