SARBuD1.0： A SAR building dataset based on GF-3 FSII imageries for built-up area extraction with deep learning method

WU Fan; ZHANG Hong; WANG Chao; LI Lu; LI Juanjuan; CHEN Weirong; ZHANG Bo

doi:10.11834/jrs.20220296

Data Articles | Views : 0 下载量: 486 CSCD: 0 更多指标

R-PDF
PDF
Export
Share
Collection
Album

SARBuD1.0： A SAR building dataset based on GF-3 FSII imageries for built-up area extraction with deep learning method
Vol. 26, Issue 4, Pages: 620-631(2022)
Published： 07 April 2022 ，
DOI： 10.11834/jrs.20220296

扫描看全文

吴樊，张红，王超，李璐，李娟娟，陈卫荣，张波.2022.SARBuD 1.0：面向深度学习的GF-3 精细模式SAR建筑数据集.遥感学报，26（4）： 620-631

Wu F，Zhang H，Wang C，Li L，Li J J，Chen W R and Zhang B. 2022. SARBuD1.0： A SAR Building Dataset Based on GF-3 FSII Imageries for Built-up Area Extraction with Deep Learning Method. National Remote Sensing Bulletin， 26（4）：620-631
吴樊，张红，王超，李璐，李娟娟，陈卫荣，张波.2022.SARBuD 1.0：面向深度学习的GF-3 精细模式SAR建筑数据集.遥感学报，26（4）： 620-631 DOI： 10.11834/jrs.20220296.

Wu F，Zhang H，Wang C，Li L，Li J J，Chen W R and Zhang B. 2022. SARBuD1.0： A SAR Building Dataset Based on GF-3 FSII Imageries for Built-up Area Extraction with Deep Learning Method. National Remote Sensing Bulletin， 26（4）：620-631 DOI： 10.11834/jrs.20220296.

摘要

合成孔径雷达SAR（Synthetic Aperture Radar）是开展城市建筑区信息获取与动态监测的重要数据源。本文建立了一个面向深度学习建筑区提取的中高分辨率SAR建筑区数据集SARBuD1.0 （SAR BUilding Dataset）。该数据集包含了覆盖中国不同区域的27景高分三号（GF-3）精细模式SAR图像，并从中获取了建筑区共计60000个SAR样本数据，结合光学图像与专家解译，制作了与样本数据对应的标签图像。SARBuD1.0数据集包含了不同地形场景类型、不同分布类型、不同区域的建筑区。该数据集可支持研究者对建筑区进行图像特征分析、辅助图像理解，并可对当前热点深度学习方法提供训练、测试数据支持。本文以山区建筑为例，使用传统纹理特征与深度学习特征对建筑区进行了特征分析与比较，相比于传统的人工设计的纹理特征，卷积神经网络具有更深、更多的特征，利用网络模型浅层的不同卷积核采样可得到各种纹理特征，在网络的深层卷积结构中可获取代表着类别的深层语义特征，使得分类器能更好地检测并提取图像中指定的目标。基于本数据集利用深度学习方法对不同地形区域的建筑区进行提取实验。实验结果表明基于本数据集训练的深度学习模型，对建筑区提取可以取得良好的结果，说明该数据集可以很好支持面向大数据的深度学习方法。其他学者可以基于SARBuD1.0数据集开展建筑区图像特征分析与语义分割提取等方面的研究。

Abstract

Synthetic Aperture Radar (SAR) is one of the important data sources for built-up area information acquisition and dynamic monitoring. In this paper

SARBuD1.0

a SAR image patch dataset of built-up area with GF-3 Fine strip-map mode

is introduced.

The dataset is derived from 27 scenes of 10 m resolution GF-3 SAR images covering different regions in China. Approximately 60000 samples of built-up area are obtained from the SAR images. The dataset consists of built-up area SAR image patches and corresponding label images that are interpreted by experts with high-resolution optical images. The dataset contains built-up areas of different distribution types and different regions. The terrain scenes of the samples include plain area

mountain area

and plateau. The SARBuD1.0 dataset can support researchers to analyze the image features of built-up areas in different regions

assist in SAR image understanding

and provide training and test data for deep learning methods for built-up area segmentation in SAR images.

In this paper

using built-up areas in mountain areas as an example

the traditional texture features and deep learning features of the built-up area are analyzed. Experiments show that a convolution neural network can provide deeper features of built-up areas compared with traditional texture features. Features in different scales can be obtained by the shallow convolutional layers of the network

and semantic information can be obtained by the deep layers. Therefore

the deep convolutional neural network classifier can detect and extract the built-up area better. Based on the dataset

three deep learning methods are applied to extract the built-up area in different terrain areas. The experimental results show that the deep learning models can achieve good results for built-up area extraction based on the dataset.

The dataset can effectively support the deep learning method for big data processing. Based on the SARBuD1.0 dataset

scholars can carry out research on feature analysis and semantic segmentation of built-up areas with SAR images.

关键词

遥感合成孔径雷达建筑数据集深度学习高分三号语义分割

Keywords

remote sensingSynthetic Aperture Radar (SAR)buildingdatasetdeep learningGF-3semantic segmentation

references

Adelipour S and Ghassemian H. 2018. Building detection in very high resolution SAR images via sparse representation over learned dictionaries. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(12): 4808-4817 [DOI: 10.1109/JSTARS.2018.2876910http://dx.doi.org/10.1109/JSTARS.2018.2876910]

Ban Y F, Jacob A and Gamba P. 2015. Spaceborne SAR data for global urban mapping at 30 m resolution using a robust urban extractor. ISPRS Journal of Photogrammetry and Remote Sensing, 103: 28-37 [DOI: 10.1016/j.isprsjprs.2014.08.004http://dx.doi.org/10.1016/j.isprsjprs.2014.08.004]

Cao H, Zhang H, Wang C and Zhang B. 2018. Operational built-up areas extraction for cities in China using sentinel-1 SAR data. Remote Sensing, 10(6): 874 [DOI: 10.3390/rs10060874http://dx.doi.org/10.3390/rs10060874]

Chen Q, Wang L, Wu Y F, Wu G M, Guo Z L and Waslander S L. 2019. TEMPORARY REMOVAL: aerial imagery for roof segmentation: a large-scale dataset towards automatic mapping of buildings. ISPRS Journal of Photogrammetry and Remote Sensing, 147: 42-55 [DOI: 10.1016/j.isprsjprs.2018.11.011http://dx.doi.org/10.1016/j.isprsjprs.2018.11.011]

China Centre for Resources Satellite Data and Application (CRESDA). 2016. GF-3 Basic Product Specification Document

中国资源卫星应用中心. 2016. 高分三号卫星产品用户手册

Chini M, Pelich R, Hostache R, Matgen P and Lopez-Martinez C. 2018. Towards a 20 m global building map from sentinel-1 SAR data. Remote Sensing, 10(11): 1833 [DOI: 10.3390/rs10111833http://dx.doi.org/10.3390/rs10111833]

Esch T, Heldens W, Hirner A, Keil M, Marconcini M, Roth A, Zeidler J, Dech S and Strano E. 2017. Breaking new ground in mapping human settlements from space–the global urban footprint. ISPRS Journal of Photogrammetry and Remote Sensing, 134: 30-42 [DOI: 10.1016/j.isprsjprs.2017.10.012http://dx.doi.org/10.1016/j.isprsjprs.2017.10.012]

Gu X C, Fu K and Qiu X L. 2017. Fundamental Knowledge for SAR Image Interpretation.

谷秀昌, 付琨, 仇晓兰. 2017. SAR图像判读解译基础. 北京: 科学出版社

He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90]

Ji S P, Wei S Q and Lu M. 2019. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing, 57(1): 574-586 [DOI: 10.1109/TGRS.2018.2858817http://dx.doi.org/10.1109/TGRS.2018.2858817]

Li L. 2020. Built-up Area Intelligent Extraction and Change Detection with SAR Images Over Large Scale Space. Beijing: University of Chinese Academy of Sciences

李璐. 2020. SAR图像大空间尺度建筑区智能提取与变化检测研究. 北京: 中国科学院大学

Li X, Su J and Yang L. 2020. Building detection in SAR images based on bi-dimensional empirical mode decomposition algorithm. IEEE Geoscience and Remote Sensing Letters, 17(4): 641-645 [DOI: 10.1109/LGRS.2019.2928965http://dx.doi.org/10.1109/LGRS.2019.2928965]

Shahzad M, Maurer M, Fraundorfer F, Wang Y Y and Zhu X X. 2019. Buildings detection in VHR SAR images using fully convolution neural networks. IEEE Transactions on Geoscience and Remote Sensing, 57(2): 1100-1116 [DOI: 10.1109/TGRS.2018.2864716http://dx.doi.org/10.1109/TGRS.2018.2864716]

Sun Z C, Xu R, Du W J, Wang L and Lu D S. 2019. High-resolution urban land mapping in China from sentinel 1A/2 imagery based on Google earth engine. Remote Sensing, 11(7): 752 [DOI: 10.3390/rs11070752http://dx.doi.org/10.3390/rs11070752]

Tavares P A, Beltrão N E S, Guimarães U S and Teodoro A C. 2019. Integration of Sentinel-1 and Sentinel-2 for classification and LULC mapping in the urban area of Belém, eastern Brazilian Amazon. Sensors, 19(5): 1140 [DOI: 10.3390/s19051140http://dx.doi.org/10.3390/s19051140]

Thiele A, Cadario E, Schulz K, Thonnessen U and Soergel U. 2007. Building recognition from multi-aspect high-resolution InSAR data in urban areas. IEEE Transactions on Geoscience and Remote Sensing, 45(11): 3583-3593 [DOI: 10.1109/TGRS.2007.898440http://dx.doi.org/10.1109/TGRS.2007.898440]

Wei S S, Zhang H, Wang C, Wang Y Y and Xu L. 2019. Multi-temporal SAR data large-scale crop mapping based on U-Net model. Remote Sensing, 11(1): 68 [DOI: 10.3390/rs11010068http://dx.doi.org/10.3390/rs11010068]

Woo S, Park J, Lee J Y and Kweon I S. 2018. CBAM: convolutional block attention module//Proceedings of the 15th European Conference on Computer Vision. Munich: Springer: 3-19 [DOI: 10.1007/978-3-030-01234-2_1http://dx.doi.org/10.1007/978-3-030-01234-2_1]

Zhang H, Wang C, Zhang B, Wu F and Yan D M. 2009. Object Recognition with High Resolution SAR Image. Beijing: China Science Publishing and Media Ltd

张红, 王超, 张波, 吴樊, 闫冬梅. 2009. 高分辨率SAR图像目标识别. 北京: 科学出版社

Zhang Q J. 2017. System design and key technologies of the GF-3 satellite. Acta Geodaetica et Cartographica Sinica, 46(3): 269-277

张庆君. 2017. 高分三号卫星总体设计与关键技术. 测绘学报, 46(3): 269-277 [DOI: 10.11947/j.AGCS.2017.20170049http://dx.doi.org/10.11947/j.AGCS.2017.20170049]

Zhang Z H, Guo W W, Yu W H and Yu W X. 2019. Multi-task fully convolutional networks for building segmentation on SAR image. The Journal of Engineering, 2019(20): 7074-7077 [DOI: 10.1049/joe.2019.0569http://dx.doi.org/10.1049/joe.2019.0569]

Zhang Z X, Liu Q J and Wang Y H. 2018. Road extraction by deep residual U-Net. IEEE Geoscience and Remote Sensing Letters, 15(5): 749-753 [DOI: 10.1109/LGRS.2018.2802944http://dx.doi.org/10.1109/LGRS.2018.2802944]

Zhao J P, Zhang Z H, Yao W, Datcu M, Xiong H L and Yu W X. 2020. OpenSARUrban: a Sentinel-1 SAR image dataset for urban interpretation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 187-203 [DOI: 10.1109/JSTARS.2019.2954850http://dx.doi.org/10.1109/JSTARS.2019.2954850]

Zhu J Y, Park T, Isola P and Efros A A. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. 2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE: 2242-2251 [DOI: 10.1109/ICCV.2017.244http://dx.doi.org/10.1109/ICCV.2017.244]

Alert me when the article has been cited

提交

Point cloud benchmark dataset WHU-TLS and WHU-MLS for deep learning

MtSCCD： Land-use scene classification and change-detection dataset for deep learning

Optical-signal token guided change detection network for heterogeneous remote sensing image

Research progress on hyperspectral anomaly detection

Hyperspectral remote sensing image classification based on multidirectional adaptive aware network