Remote sensing image urban built-up area extraction and optimization method based on PSPNet

doi:10.6046/gtzyyg.2020.04.12

Abstract
Figures/Tables
References
Related Articles
Metrics

Download: PDF(3553 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Using high-resolution satellite remote sensing images to extract the boundary of the built-up area is of great significance for urban expansion monitoring and urban development planning. In order to obtain high-precision and high-resolution built-up area data, this study uses the NDBI index and artificial visual interpretation methods to construct remote sensing image datasets of urban built-up areas and uses traditional machine learning methods and four deep learning methods including PSPNet semantic segmentation network to extract the built-up area of Sentinel-2 images. The training results show that the PSPNet network has the highest accuracy for the built-up area extraction (IOU of the training set is 79.5%). This paper employs Overlapsize method to optimize the extraction results of PSPNet, which further improves the accuracy of the built-up area extraction. The IOU on the training set reaches 80.5%, and the IOU on the test set reaches 83.1%. Compared with the traditional machine learning method, the method of PSPNet + Overlapsize has practical application significance in built-up area extracting.

Keywords built-up area extraction deep learning convolutional neural network semantic segmentation PSPNet Overlapsize

TP79

Issue Date: 23 December 2020

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Zhao LIU
	Feifan LIAO
	Tong ZHAO

Cite this article:

Zhao LIU,Feifan LIAO,Tong ZHAO. Remote sensing image urban built-up area extraction and optimization method based on PSPNet[J]. Remote Sensing for Land & Resources, 2020, 32(4): 84-89.

URL:

https://www.gtzyyg.com/EN/10.6046/gtzyyg.2020.04.12 OR https://www.gtzyyg.com/EN/Y2020/V32/I4/84

Fig.1 Basic structure of PSPNet

Fig.2 Training extraction flow chart

Fig.3 Partial city images and annotated data

Fig.4 Training results

Fig.5 Method schematic of Overlapsize

Fig.6 Extraction results of built-up area before and after using Overlapsize

Fig.7 Comparison of improvement effects

[1]	中华人民共和国建设部. GB/T50280—98城市规划基本术语标准[S]. 工程建设标准全文信息系统, 1999.
[1]	Ministry of Construction P.R.China. GB/T50280—98 standard for basic terminology of urban planning[S]. Engineering Construction Standard Full-Text Information System, 1999.
[2]	Masek J G, Lindsay F E, Goward S N. Dynamics of urban growth in the Washington DC metropolitan area,1973—1996,from Landsat observations[J]. International Journal of Remote Sensing, 2000,21(18):3473-3486.
[3]	刘智丽, 张启斌, 岳德鹏, 等. 基于Sentinel-2A与NPP-VIIRS夜间灯光数据的城市建成区提取[J]. 国土资源遥感, 2019,31(4):227-234.doi: 10.6046/gtzyyg.2019.04.29.
[3]	Liu Z L, Zhang Q B, Yue D P, et al. Extraction of urban built-up areas based on Sentinel-2A and NPP-VIIRS nighttime light data[J]. Remote Sensing for Land and Resource, 2019,31(4):227-234.doi: 10.6046/gtzyyg.2019.04.29.
[4]	于清永. 利用中高分辨率影像对城市建成区信息提取的方法研究[D]. 阜新:辽宁工程技术大学, 2016.
[4]	Yu Q Y. Research on information extraction of urban built-up area by using medium and high resolution images[D]. Fuxin:Liaoning Technical University, 2016.
[5]	闫晓天. 基于支持向量机及MODIS数据的南昌市城市空间格局演变研究[D]. 南昌:东华理工大学, 2016.
[5]	Yan X T. Study on evolution of urban spatial pattern of Nanchang base on support vector machine and MODIS data[D]. Nanchang:East China University of Technology, 2016.
[6]	冯丽英. 基于深度学习技术的高分辨率遥感影像建设用地信息提取研究[D]. 杭州:浙江大学, 2017.
[6]	Feng L Y. Research on construction land information extraction from high resolution images with deep learning technology[D]. Hangzhou:Zhejiang University, 2017.
[7]	马凯, 罗泽. 基于卷积神经网络的青海湖区域遥感影像分类[J]. 计算机系统应用, 2018,27(9):137-142.
[7]	Ma K, Luo Z. Classification of remote sensing images in Qinghai Lake based on convolutional neural network[J]. Computer Systems and Applications, 2018,27(9):137-142.
[8]	陈磊士, 赵俊三, 董智文, 等. 基于深度学习的滇中城市多光谱影像建设用地信息提取[J]. 软件导刊, 2018,17(11):177-180,186.
[8]	Chen L S, Zhao J S, Dong Z W, et al. Urban construction land information extraction based on deep learning by multi-spectral remote sensing imagery of Yunnan central urban agglomeration area[J]. Software Guide, 2018,17(11):177-180,186.
[9]	Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE, 2017:2881-2890.
[10]	Jonathan L, Evan S, Trevor D. Fully convolutional networks for semantic segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE, 2015:3431-3440.
[11]	He K, Zhang X, Ren S, et al. Deep residual learning for image reco-gnition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE, 2016:770-778.
[12]	Wang T, He P L. The classification algorithm based on the cross entropy rule and new activation function in fuzzy neural network[C]// 2005 International Conference on Machine Learning and Cybernetics.Guangzhou:IEEE, 2005,8:4631-4635.
[13]	Kingma D P, Ba J. Adam:A method for stochastic optimization[EB/OL]. (2014-12-22)[2019-10-01]. https://arxiv.org/pdf/1412.6980.pdf. url: https://arxiv.org/pdf/1412.6980.pdf
[14]	肖莹光. 从部门协调的角度看建成区和规划建设用地的定义和划定[C]// 中国城市规划学会、重庆市人民政府.规划创新:2010中国城市规划年会论文集.中国城市规划学会、重庆市人民政府:中国城市规划学会, 2010:120-124.
[14]	Xiao Y G. Definition and delineation of built-up areas and planned construction land from the perspective of department coordination[C]// Urban Planning Society of China,Chongqing Municipal Government. Planning and Innovation:Essays of 2010 Annual National Planning Conference.Urban Planning Society of China,Chongqing Municipal Government:Urban Planning Society of China, 2010:120-124.
[15]	李爱民. 基于遥感影像的城市建成区扩张与用地规模研究[D]. 郑州:解放军信息工程大学, 2009.
[15]	Li A M. Research on urban built-up area expansion and land use scale based on remote sensing[D]. Zhengzhou:Information Engineering University, 2009.
[16]	Zha Y, Gao J, Ni S. Use of normalized difference built-up index in automatically mapping urban areas from TM imagery[J]. Remote Sensing, 2003,24(3):583-594.
[17]	Zhang H, Dana K, Shi J, et al. Context encoding for semantic segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE, 2018:7151-7160.
[18]	Chen L C, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL]. (2017-06-17)[2019-06-01]. https://arxiv.org/pdf/1706.05587.pdf. url: https://arxiv.org/pdf/1706.05587.pdf
[19]	Zhou L C, Zhang C, Wu M. D-LinkNet:LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE, 2018:182-186.
[20]	Zhuang J, Yang J L, Gu L, et al. ShelfNet for fast semantic segmentation[EB/OL]. (2019-09-04)[2019-10-01]. https://arxiv.org/pdf/1811.11254.pdf. url: https://arxiv.org/pdf/1811.11254.pdf

[1]	XUE Bai, WANG Yizhe, LIU Shuhan, YUE Mingyu, WANG Yiying, ZHAO Shihu. Change detection of high-resolution remote sensing images based on Siamese network[J]. Remote Sensing for Natural Resources, 2022, 34(1): 61-66.
[2]	GUO Xiaozheng, YAO Yunjun, JIA Kun, ZHANG Xiaotong, ZHAO Xiang. Information extraction of Mars dunes based on U-Net[J]. Remote Sensing for Natural Resources, 2021, 33(4): 130-135.
[3]	YU Xinli, SONG Yan, YANG Miao, HUANG Lei, ZHANG Yanjie. Multi-model and multi-scale scene recognition of shipbuilding enterprises based on convolutional neural network with spatial constraints[J]. Remote Sensing for Natural Resources, 2021, 33(4): 72-81.
[4]	FENG Dongdong, ZHANG Zhihua, SHI Haoyue. Fine extraction of urban villages in provincial capitals based on multivariate data[J]. Remote Sensing for Natural Resources, 2021, 33(3): 272-278.
[5]	WU Yu, ZHANG Jun, LI Yixu, HUANG Kangyu. Research on building cluster identification based on improved U-Net[J]. Remote Sensing for Land & Resources, 2021, 33(2): 48-54.
[6]	LU Qi, QIN Jun, YAO Xuedong, WU Yanlan, ZHU Haochen. Buildings extraction of GF-2 remote sensing image based on multi-layer perception network[J]. Remote Sensing for Land & Resources, 2021, 33(2): 75-84.
[7]	AN Jianjian, MENG Qingyan, HU Die, HU Xinli, YANG Jian, YANG Tianliang. The detection and determination of the working state of cooling tower in the thermal power plant based on Faster R-CNN[J]. Remote Sensing for Land & Resources, 2021, 33(2): 93-99.
[8]	GUO Wen, ZHANG Qiao. Building extraction using high-resolution satellite imagery based on an attention enhanced full convolution neural network[J]. Remote Sensing for Land & Resources, 2021, 33(2): 100-107.
[9]	QIU Yifan, CHAI Dengfeng. A deep learning method for Landsat image cloud detection without manually labeled data[J]. Remote Sensing for Land & Resources, 2021, 33(1): 102-107.
[10]	LIU Zhao, ZHAO Tong, LIAO Feifan, LI Shuai, LI Haiyang. Research and comparative analysis on urban built-up area extraction methods from high-resolution remote sensing image based on semantic segmentation network[J]. Remote Sensing for Land & Resources, 2021, 33(1): 45-53.
[11]	CAI Xiang, LI Qi, LUO Yan, QI Jiandong. Surface features extraction of mining area image based on object-oriented and deep-learning method[J]. Remote Sensing for Land & Resources, 2021, 33(1): 63-71.
[12]	ZHENG Zhiteng, FAN Haisheng, WANG Jie, WU Yanlan, WANG Biao, HUANG Tengjie. An improved double-branch network method for intelligently extracting marine cage culture area[J]. Remote Sensing for Land & Resources, 2020, 32(4): 120-129.
[13]	DU Fangzhou, SHI Yuli, SHENG Xia. Research on downscaling of TRMM precipitation products based on deep learning: Exemplified by northeast China[J]. Remote Sensing for Land & Resources, 2020, 32(4): 145-153.
[14]	PEI Chan, LIAO Tiejun. Multi-scale architecture search method for remote sensing object detection[J]. Remote Sensing for Land & Resources, 2020, 32(4): 53-60.
[15]	WEI Hongyu, ZHAO Yindi, DONG Jihong. Cooling tower detection based on the improved RetinaNet[J]. Remote Sensing for Land & Resources, 2020, 32(4): 68-73.

Viewed

Full text

Abstract

Cited

Shared

Discussed