Inundation monitoring of immovable cultural relics with time-series SAR images

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

doi:10.11834/jrs.20211146

Remote Sensing Applications | Views : 0 下载量: 473 CSCD: 1 更多指标

PDF
Export
Share
Collection
Album

Inundation monitoring of immovable cultural relics with time-series SAR images
Vol. 25, Issue 12, Pages: 2431-2440(2021)
Published： 07 December 2021 ，
DOI： 10.11834/jrs.20211146

扫描看全文

吴樊，李娟娟，张波，王超，张红，陈富龙，李璐，许璐.2021.时间序列SAR图像不可移动文物水域淹没监测.遥感学报，25（12）： 2431-2440

Wu F，Li J J，Zhang B，Wang C，Zhang H，Chen F L，Li L and Xu L. 2021. Inundation monitoring of immovable cultural relics with time-series SAR images. National Remote Sensing Bulletin， 25（12）：2431-2440
吴樊，李娟娟，张波，王超，张红，陈富龙，李璐，许璐.2021.时间序列SAR图像不可移动文物水域淹没监测.遥感学报，25（12）： 2431-2440 DOI： 10.11834/jrs.20211146.

Wu F，Li J J，Zhang B，Wang C，Zhang H，Chen F L，Li L and Xu L. 2021. Inundation monitoring of immovable cultural relics with time-series SAR images. National Remote Sensing Bulletin， 25（12）：2431-2440 DOI： 10.11834/jrs.20211146.

摘要

全球气候变化引起的极端降雨、洪涝灾害是导致不可移动文物受损的重要破坏因素。合成孔径雷达SAR（Synthetic Aperture Radar）具有全天时、全天候、大范围周期性对地观测的优势，是大区域水体监测的重要手段，对不可移动文物水域淹没及风险监测具有重要意义。本文利用时间序列SAR图像提出基于残差U-Net的不可移动文物水域淹没及风险监测框架。首先，基于双峰阈值分割法结合专家知识辅助进行水体样本生成，提高样本制作效率；其次，引入残差模块建立U型卷积网络，综合残差结构及U-Net的特点，缓解梯度更新时的弥散、消失等现象，通过卷积层之间累加和跳跃链接，保留多尺度的地物特征信息，以实现水体快速、高精度的语义分割；最后通过将结果与不可移动文物点位进行空间叠加分析，实现对不可移动文物水淹状况的监测。选取鄱阳湖及南昌市昌邑北垱遗址作为试验研究对象。获取了21景覆盖鄱阳湖区域不同时相Sentinel-1 SAR图像，并结合Sentinel-2光学图像进行结果分析与评价。实验结果表明：本文方法在鄱阳湖试验区对水体提取总精度优于95%，相较于FCN（Fully Convolutional Networks）与U-Net方法具有更好的精度。利用不同时相SAR图像获得时间序列水体分布范围变化图，与昌邑北垱遗址点位进行空间叠加分析，得到不可移动文物水域淹没长时间序列监测结果。实验结果表明本文提出的方法可以有效提取水体范围，对不可移动文物水域淹没及风险监测可以提供有力支撑。

Abstract

Immovable cultural relics are crucial material in cultural heritage. In recent years

meteorological and hydrological disasters

such as flood storms and other disasters

have been a significant threat to immovable cultural relics due to global climate change

torrential weather

and other extreme weather. Thus

extensive mapping and dynamic monitoring of water bodies timely are essential. Synthetic Aperture Radar (SAR) has the advantages of all-day

all-weather

and large-scale periodic earth observation and plays a key role in the application of large-scale water body monitoring.

In this paper

a framework for monitoring inundation and risk of immovable cultural heritage based on residual U-Net is proposed by using time series SAR images. First

on the basis of the bimodal threshold segmentation method and combined with expert knowledge

water sample generation was carried out to improve the efficiency of the sample production. Second

the U-shaped convolutional network was established by introducing the residual module

which combined the characteristics of the residual structure and U-Net to alleviate the gradient dispersion and disappearance during the value updating. By accumulating and jumping links between convolutional layers

more feature information of objects is retained to achieve rapid and high-precision semantic segmentation of water bodies. Finally

by superimposing the water extraction results with the area of immovable cultural relics

the waterlogging status of immovable cultural relics can be monitored.

Poyang Lake and the relic of Changyi Beidang in Nanchang were selected for the experiments. A total of 21 Sentinel-1 images covering Poyang Lake at different dates were obtained for water body extraction. The results were analyzed and evaluated by combining corresponding Sentinel-2 optical images. The experimental results show that the overall accuracy of the proposed method in the Poyang Lake experimental area is greater than 95%

and the proposed method outperforms Fully Convolutional Networks (FCN) and U-Net methods.

Spatial superposition analysis was conducted combining the site of relic of Changyi with the monitoring results of water bodies from SAR images in long-term series. The experimental results unveil that the method proposed in this paper can extract water bodies and has great potential for inundation and risk monitoring of immovable cultural relics.

关键词

遥感合成孔径雷达不可移动文物水体提取深度学习洪水监测

Keywords

remote sensingSynthetic Aperture Radarimmovable cultural relicswater extractiondeep learningflooding monitoring

references

Benoudjit A and Guida R. 2019. A novel fully automated mapping of the flood extent on SAR images using a supervised classifier. Remote Sensing, 11(7): 779 [DOI: 10.3390/rs11070779http://dx.doi.org/10.3390/rs11070779]

Cao H, Zhang H, Wang C and Zhang B. 2019. Operational flood detection using Sentinel-1 SAR data over large areas. Water, 11(4): 786 [DOI: 10.3390/w11040786http://dx.doi.org/10.3390/w11040786]

Chinese Academy of Cultural Heritage. 2018. Status and trend analysis of China’s world cultural heritage protection and management—annual report of China’s world cultural heritage in 2017. China Cultrual Heritage, (6): 4-28 (中国文化遗产研究院. 2018. 我国世界文化遗产保护管理状况及趋势分析——中国世界文化遗产2017年度总报告. 中国文化遗产, (6): 4-28)

Chinese Academy of Cultural Heritage. 2019. Status and trend analysis of China’s world cultural heritage protection and management—annual report of China’s world cultural heritage in 2018. China Cultrual Heritage, (6): 4-26 (中国文化遗产研究院. 2019. 我国世界文化遗产保护管理状况及趋势分析—中国世界文化遗产2018年度总报告. 中国文化遗产, (6): 4-26)

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, NV, USA: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90]

Kang W C, Xiang Y M, Wang F, Wan L and You H J. 2018. Flood detection in Gaofen-3 SAR images via fully convolutional networks. Sensors, 18(9): 2915 [DOI: 10.3390/s18092915http://dx.doi.org/10.3390/s18092915]

Li D, Wu B S, Chen B W, Xue Y and Zhang Y. 2020. Review of water body information extraction based on satellite remote sensing. Journal of Tsinghua University (Science and Technology), 60(2): 147-161

李丹, 吴保生, 陈博伟, 薛源, 张翼. 2020. 基于卫星遥感的水体信息提取研究进展与展望. 清华大学学报(自然科学版), 60(2): 147-161 [DOI: 10.16511/j.cnki.qhdxxb.2019.22.038http://dx.doi.org/10.16511/j.cnki.qhdxxb.2019.22.038]

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 W, Sun G L, Long H Y, Zheng X M, Wang L and Wang H L. 2018. Research progress of urban hydrological disaster risk assessment from 1988 to 2017. Journal of Sichuan University of Science and Engineering (Natural Science Edition), 31(4): 74-82

李星苇, 孙桂丽, 龙泓宇, 郑夏明, 王立, 王含露. 2018. 1988-2017年城市水文灾害风险评估研究进展. 四川理工学院学报(自然科学版), 31(4): 74-82 [DOI: 10.11863/j.suse.2018.04.12http://dx.doi.org/10.11863/j.suse.2018.04.12]

Li Y, Martinis S and Wieland M. 2019. Urban flood mapping with an active self-learning convolutional neural network based on TerraSAR-X intensity and interferometric coherence. ISPRS Journal of Photogrammetry and Remote Sensing, 152: 178-191 [DOI: 10.1016/j.isprsjprs.2019.04.014http://dx.doi.org/10.1016/j.isprsjprs.2019.04.014]

Liu T, Fang J, Ma H and Shi P J. 2019. Spatiotemporal patterns and influencing factors of mortality of climatological-meteorological-hydrological disaster in the world (1965-2016). Journal of Natural Disasters, 28(3): 8-16

刘甜, 方建, 马恒, 史培军. 2019. 全球陆地气候气象及水文灾害死亡人口时空格局及影响因素分析(1965—2016年). 自然灾害学报, 28(3): 8-16 [DOI: 10.13577/j.jnd.2019.0302http://dx.doi.org/10.13577/j.jnd.2019.0302]

Long J, Shelhamer E and Darrell T. 2015. Fully convolutional networks for semantic segmentation//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE: 3431-3440 [DOI: 10.1109/CVPR.2015.7298965http://dx.doi.org/10.1109/CVPR.2015.7298965]

Matthieu B, Johnsen H and Piantaida R. 2016. Sentinel-1 product definition. ESA, S1-RS-MDA-52-7440. [2021-05-03]. https://sentinel.esa.int/documents/247904/1877131/Sentinel-1-Product-Definitionhttps://sentinel.esa.int/documents/247904/1877131/Sentinel-1-Product-Definition

Nemni E, Bullock J, Belabbes S and Bromley L. 2020. Fully convolutional neural network for rapid flood segmentation in synthetic aperture radar imagery. Remote Sensing, 12(16): 2532 [DOI: 10.3390/rs12162532http://dx.doi.org/10.3390/rs12162532]

People’s Government of Jiangxi Province. 2019. List of protection scope of the sixth batch of cultural relic protection units in Jiangxi province. [2021-02-10]. http://www.jiangxi.gov.cn/art/2019/3/19/art_4969_669671.html (江西省人民政府. 2019.

第六批江西省文物保护单位保护范围一览表. [2021-02-10]. http://www.jiangxi.gov.cn/art/2019/3/19/art_4969_669671.htmlhttp://www.jiangxi.gov.cn/art/2019/3/19/art_4969_669671.html

Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//Proceeding of Medical Image Computing and Computer-Assisted Intervention. Munich, Germany: Springer: 234-241 [DOI:10.1007/978-3-319-24574-4_28http://dx.doi.org/10.1007/978-3-319-24574-4_28]

Shen X Y, Wang D C, Mao K B, Anagnostou E and Hong Y. 2019. Inundation extent mapping by synthetic aperture radar: a review. Remote Sensing, 11(7): 879 [DOI: 10.3390/rs11070879http://dx.doi.org/10.3390/rs11070879]

Simon R N, Tormos T and Danis P A. 2014. Geographic object based image analysis using very high spatial and temporal resolution radar and optical imagery in tracking water level fluctuations in a freshwater reservoir. South-Eastern European Journal of Earth Observation and Geomatics, 3(2S): 287-291

Sun F D and Ma R H. 2020. Hydrologic changes of Poyang Lake based on radar altimeter and optical sensor. Acta Geographica Sinica, 75(3): 544-557

孙芳蒂, 马荣华. 2020. 鄱阳湖水文特征动态变化遥感监测. 地理学报, 75(3): 544-557 [DOI: 10.11821/dlxb202003008http://dx.doi.org/10.11821/dlxb202003008]

Torres R, Navas-Traver I, Bibby D, Lokas S, Snoeij P, Rommen B, Osborne S, Ceba-Vega F, Potin P and Geudtner D. 2017. Sentinel-1 SAR system and mission//IEEE Radar Conference (RadarConf). Seattle, WA, USA: IEEE: 1582-1585 [DOI: 10.1109/RADAR.2017.7944460http://dx.doi.org/10.1109/RADAR.2017.7944460]

Tsyganskaya V, Martinis S and Marzahn P. 2019. Flood monitoring in vegetated areas using multitemporal Sentinel-1 data: impact of time series features. Water, 11(9): 1938 [DOI: 10.3390/w11091938http://dx.doi.org/10.3390/w11091938]

Yao S M, Lei W T, Qu G, Chai Z H and Luan H L. 2020. Analysis on inundation condition in Poyang Lake during flood season of 2020 based on satellite image. Yangtze River, 51(12): 185-190

姚仕明, 雷文韬, 渠庚, 柴朝晖, 栾华龙. 2020. 基于遥感影像的鄱阳湖2020年汛期灾情分析. 人民长江, 51(12): 185-190 [DOI: 10.16232/j.cnki.1001-4179.2020.12.033http://dx.doi.org/10.16232/j.cnki.1001-4179.2020.12.033]

Zhang W, Cui C L, Li L Y, Jia Y L and Meng L K. 2019. Analysis of relationship between water area and water level based on long-term observation in Poyang Lake. Journal of China Hydrology, 39(3): 29-35, 21

张文, 崔长露, 李林宜, 贾祎琳, 孟令奎. 2019. 基于长时间序列遥感数据的鄱阳湖水面面积监测分析. 水文, 39(3): 29-35, 21 [DOI: 10.3969/j.issn.1000-0852.2019.03.005http://dx.doi.org/10.3969/j.issn.1000-0852.2019.03.005]

Zhou S L, Kan P Y, Silbernagel J and Jin J F. 2020. Application of image segmentation in surface water extraction of freshwater lakes using radar data. ISPRS International Journal of Geo-Information, 9(7): 424 [DOI: 10.3390/ijgi9070424http://dx.doi.org/10.3390/ijgi9070424]

Zhu X X, Montazeri S, Ali M, Hua Y S, Wang Y Y, Mou L C, Shi Y L, Xu F and Bamler R. 2021. Deep learning meets SAR: concepts, models, pitfalls, and perspectives. IEEE Geoscience and Remote Sensing Magazine, PP(99) [DOI: 10.1109/MGRS.2020.3046356]

Alert me when the article has been cited

提交

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

Weakly supervised scale adaptation data augmentation for scene classification of high-resolution remote sensing images

Urban cinnamomum camphora crown detection research using RGB-DSM images and deep learning