Please wait a minute...
 
Remote Sensing for Natural Resources    2024, Vol. 36 Issue (3) : 96-107     DOI: 10.6046/zrzyyg.2023132
|
Information extraction of landslides based on high-resolution remote sensing images and an improved U-Net model: A case study of Wenchuan, Sichuan
BAI Shi1(), TANG Panpan1(), MIAO Zhao2, JIN Caifeng3, ZHAO Bo1, WAN Haoming1
1. Research Center of Big Data Technology, Nanhu Laboratory, Jiaxing 314002, China
2. Institute of Exploration Technology Chinese Academy of Geological Sciences, Chengdu 611734, China
3. School of Architectural Engineering, Jiaxing Nanhu University, Jiaxing 314001, China
Download: PDF(7655 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

Rapid identification and detection of landslides can both meet the requirement of timely responses to disasters and hold great significance for loss assessment and rescue post-disaster. This study proposed a deep learning-based automatic information extraction method for landslides to improve their detection accuracy. Specifically, the model input of this method includes the remote sensing images of the target areas, data from digital elevation models, and variation characteristics extracted using robust change vector analysis (RCVA). Furthermore, a U-Net model integrating dense upsampling and asymmetric convolution is designed to improve the identification accuracy. Taking Wenchuan, Sichuan Province as the study area, this study designed experiments to test the pixel-level image segmentation accuracy of landslides using different data combinations and methods. The results indicate that the improved U-Net model proposed in the study can produce the optimal image segmentation results of landslides.
Keywords deep learning      landslide      semantic segmentation      U-Net     
ZTFLH:  TP79  
Issue Date: 03 September 2024
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Shi BAI
Panpan TANG
Zhao MIAO
Caifeng JIN
Bo ZHAO
Haoming WAN
Cite this article:   
Shi BAI,Panpan TANG,Zhao MIAO, et al. Information extraction of landslides based on high-resolution remote sensing images and an improved U-Net model: A case study of Wenchuan, Sichuan[J]. Remote Sensing for Natural Resources, 2024, 36(3): 96-107.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2023132     OR     https://www.gtzyyg.com/EN/Y2024/V36/I3/96
Fig.1  Location of the study area and Google Earth remote sensing image
Fig.2  Landslide extraction process
Fig.3  Improved U-Net network model structure
Fig.4  Dense upsampling diagram
Fig.5  Landslide interpretation result
数据构成 IoU Precision Recall F1-score 浮点运算次数/109 参数量/106
RGB 0.68 0.80 0.85 0.79 160.7 17.3
RGB+DEM 0.70 0.83 0.84 0.81 161.1 17.3
RGB+DEM+C 0.71 0.81 0.87 0.81 161.2 17.3
Tab.1  Effect of different input data sources on the accuracy of landslide interpretation
Fig.6  Change characteristics and landslide interpretation results before and after adding change characteristics
数据集 IoU Precision Recall F1-score 浮点运算次数/109 参数量/106
RGB+DEM 0.47 0.61 0.69 0.62 161.2 17.3
RGB+DEM+C 0.73 0.83 0.85 0.84 162.2 17.3
Tab.2  Effects of changing characteristics on the accuracy of landslide interpretation
模型 IoU Precision Recall F1-score 浮点运算次数/109 参数量/106
U-Net+AC+DUC 0.76 0.84 0.90 0.85 192.8 56.5
ResU-Net 0.62 0.68 0.91 0.73 324.9 13.0
DeeplabV3+ 0.62 0.75 0.82 0.74 89.6 59.3
UperNet 0.65 0.79 0.82 0.76 183.1 126.1
HATNet 0.63 0.77 0.80 0.75 65.0 70.4
Convnext 0.54 0.86 0.62 0.69 193.7 138.0
Swin-Transformer 0.50 0.56 0.81 0.60 264.8 138.0
Tab.3  Comparison results of common segmentation network and improved U-Net network evaluation index
序号 图像 标签 U-Net+
AC+DUC		 ResU-Net DeeplabV3+ UperNet HATNet Conv
next		 Swin-
Transformer
a
b
c
d
e
f
g
Tab.4  Interpretation results of different models of landslides
模型 IoU Precision Recall F1-score 浮点运算次数/109 参数量/106
U-Net 0.71 0.81 0.87 0.81 161.2 17.3
U-Net+AC 0.71 0.81 0.88 0.81 198.0 20.4
U-Net+DUC 0.75 0.82 0.90 0.84 155.9 53.4
U-Net+AC+DUC 0.76 0.84 0.90 0.85 192.8 56.5
Tab.5  Comparison results of U-Net network evaluation indicators improved by using different strategies
序号 图像 标签 U-Net U-Net+AC U-Net
+DUC		 U-Net
+AC+DUC
a
b
c
d
e
f
g
Tab.6  Comparison of interpretation results of different Model
[1] Li H, Xu Q, He Y, et al. Modeling and predicting reservoir landslide displacement with deep belief network and EWMA control charts:A case study in Three Gorges Reservoir[J]. Landslides, 2020, 17(3):693-707.
[2] Mondini A C, Guzzetti F, Chang K T, et al. Landslide failures detection and mapping using synthetic aperture Radar:Past,present and future[J]. Earth-Science Reviews, 2021, 216:103574.
[3] Hoeppe P. Trends in weather related disasters:Consequences for insurers and society[J]. Weather and Climate Extremes, 2016, 11:70-79.
[4] Haque U, da Silva P F, Devoli G, et al. The human cost of global warming:Deadly landslides and their triggers (1995—2014)[J]. Science of the Total Environment, 2019, 682:673-684.
[5] Huggel C, Clague J J, Korup O. Is climate change responsible for changing landslide activity in high mountains?[J]. Earth Surface Processes and Landforms, 2012, 37(1):77-91.
[6] 闫琦, 李慧, 荆林海, 等. 灾后高分辨率遥感影像的地震型滑坡信息自动提取算法研究[J]. 激光与光电子学进展, 2017, 54(11):112801.
[6] Yan Q, Li H, Jing L H, et al. Automatic extraction algorithm of seismic landslide information based on after-calamity high-resolution remote sensing image[J]. Laser & Optoelectronics Progress, 2017, 54(11):112801.
[7] 朱静, 唐川. 遥感技术在我国滑坡研究中的应用综述[J]. 遥感技术与应用, 2012, 27(3):458-464.
[7] Zhu J, Tang C. An overview of remote sensing applications for landslide research in China[J]. Remote Sensing Technology and Application, 2012, 27(3):458-464.
[8] Bellotti F, Bianchi M, Colombo D, et al. Advanced InSAR techniques to support landslide monitoring[C]//Mathematics of Planet Earth.Berlin, Heidelberg:Springer, 2014:287-290.
[9] Guzzetti F, Mondini A C, Cardinali M, et al. Landslide inventory maps:New tools for an old problem[J]. Earth-Science Reviews, 2012, 112(1/2):42-66.
[10] Dou J, Yunus A P, Bui D T, et al. Improved landslide assessment using support vector machine with bagging,boosting,and stacking ensemble machine learning framework in a mountainous watershed,Japan[J]. Landslides, 2020, 17(3):641-658.
[11] Barlow J, Martin Y, Franklin S E. Detecting translational landslide scars using segmentation of Landsat ETM+ and DEM data in the northern Cascade Mountains,British Columbia[J]. Canadian Journal of Remote Sensing, 2003, 29(4):510-517.
[12] Rau J Y, Jhan J P, Rau R J. Semiautomatic object-oriented landslide recognition scheme from multisensor optical imagery and DEM[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(2):1336-1349.
[13] Rib H T, Liang T. Recognition and identification[J]. Transportation Research Board Special Report, 1978,(176).
[14] Nichol J E, Shaker A, Wong M S. Application of high-resolution stereo satellite images to detailed landslide hazard assessment[J]. Geomorphology, 2006, 76(1/2):68-75.
[15] 李晨辉, 郝利娜, 许强, 等. 面向对象的高分辨率遥感影像地震滑坡分层识别[J]. 自然资源遥感, 2023, 35(1):74-80.doi:10.6046/zrzyyg.2022013.
[15] Li C H, Hao L N, Xu Q, et al. Object-oriented hierarchical identification of earthquake-induced landslides based on high-resolution remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(1):74-80.doi:10.6046/zrzyyg.2022013.
[16] 张雨, 明冬萍, 赵文祎, 等. 基于高分光学卫星影像的泸定地震型滑坡提取与分析[J]. 自然资源遥感, 2023, 35(1):161-170.doi:10.6046/zrzyyg.2022434.
[16] Zhang Y, Ming D P, Zhao W Y, et al. The extraction and analysis of Luding earthquake-induced landslide based on high-resolution optical satellite images[J]. Remote Sensing for Natural Resources, 2023, 35(1):161-170.doi:10.6046/zrzyyg.2022434.
[17] 李松, 邓宝昆, 徐红勤, 等. 地震型滑坡灾害遥感快速识别方法研究[J]. 遥感信息, 2015, 30(4):25-28.
[17] Li S, Deng B K, Xu H Q, et al. Fast interpretation methods of landslides triggered by earthquake using remote sensing imagery[J]. Remote Sensing Information, 2015, 30(4):25-28.
[18] Marjanović M, Kovaĉević M, Bajat B, et al. Landslide susceptibility assessment using SVM machine learning algorithm[J]. Engineering Geology, 2011, 123(3):225-234.
[19] Lee S. Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data[J]. International Journal of Remote Sensing, 2005, 26(7):1477-1491.
[20] Stumpf A, Kerle N. Object-oriented mapping of landslides using random forests[J]. Remote Sensing of Environment, 2011, 115(10):2564-2577.
[21] Goetz J N, Brenning A, Petschko H, et al. Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling[J]. Computers & Geosciences, 2015, 81:1-11.
[22] He K, Zhang X, Ren S, et al. Identity mappings in deep residual networks[M]//Leibe B,Matas J,Sebe N,et al.,Eds.Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016:630-645.
[23] Chen L C, Papandreou G, Kokkinos I, et al. DeepLab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848.
[24] Girshick R. Fast R-CNN[C]// 2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile.IEEE, 2015:1440-1448.
[25] Längkvist M, Kiselev A, Alirezaie M, et al. Classification and segmentation of satellite orthoimagery using convolutional neural networks[J]. Remote Sensing, 2016, 8(4):329.
[26] Mahdianpari M, Salehi B, Rezaee M, et al. Very deep convolutional neural networks for complex land cover mapping using multispectral remote sensing imagery[J]. Remote Sensing, 2018, 10(7):1119.
[27] Ghorbanzadeh O, Blaschke T, Gholamnia K, et al. Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection[J]. Remote Sensing, 2019, 11(2):196.
[28] 杨昭颖, 韩灵怡, 郑向向, 等. 基于卷积神经网络的遥感影像及DEM滑坡识别——以黄土滑坡为例[J]. 自然资源遥感, 2022, 34(2):224-230.doi:10.6046/zrzyyg.2021204.
[28] Yang Z Y, Han L Y, Zheng X X, et al. Landslide identification using remote sensing images and DEM based on convolutional neural network:A case study of loess landslide[J]. Remote Sensing for Natural Resources, 2022, 34(2):224-230.doi:10.6046/zrzyyg.2021204.
[29] Ye C, Li Y, Cui P, et al. Landslide detection of hyperspectral remote sensing data based on deep learning with constrains[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(12):5047-5060.
[30] Wang T, Liu M, Zhang H, et al. Landslide detection based on improved YOLOv5 and satellite images[C]// 2021 4th International Conference on Pattern Recognition and Artificial Intelligence (PRAI).Yibin,China.IEEE, 2021: 367-371.
[31] Yu B, Chen F, Xu C, et al. Matrix SegNet:A practical deep learning framework for landslide mapping from images of different areas with different spatial resolutions[J]. Remote Sensing, 2021, 13(16):3158.
[32] Zhang M, Shi W, Chen S, et al. Deep multiple instance learning for landslide mapping[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(10):1711-1715.
[33] Liu P, Wei Y, Wang Q, et al. Research on post-earthquake landslide extraction algorithm based on improved U-Net model[J]. Remote Sensing, 2020, 12(5):894.
[34] Meena S R, Soares L P, Grohmann C H, et al. Landslide detection in the Himalayas using machine learning algorithms and U-Net[J]. Landslides, 2022, 19(5):1209-1229.
[35] Su Z, Chow J K, Tan P S, et al. Deep convolutional neural network-based pixel-wise landslide inventory mapping[J]. Landslides, 2021, 18(4):1421-1443.
[36] Ghorbanzadeh O, Shahabi H, Crivellari A, et al. Landslide detection using deep learning and object-based image analysis[J]. Landslides, 2022, 19(4):929-939.
[37] Oktay O, Schlemper J, Le Folgoc L, et al. Attention U-Net:Learning where to look for the pancreas[EB/OL]. 2018:arXiv:1804.03999. https://arxiv.org/abs/1804.03999.pdf.
url: https://arxiv.org/abs/1804.03999.pdf
[38] Zhou Z, Siddiquee M M R, Tajbakhsh N, et al. UNet++:Redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Transactions on Medical Imaging, 2020, 39(6):1856-1867.
[39] 龙玉洁, 李为乐, 黄润秋, 等. 汶川地震震后10 a绵远河流域滑坡遥感自动提取与演化趋势分析[J]. 武汉大学学报(信息科学版), 2020, 45(11):1792-1800.
[39] Long Y J, Li W L, Huang R Q, et al. Automatic extraction and evolution trend analysis of landslides in Mianyuan River basin in the 10 years after Wenchuan earthquake[J]. Geomatics and Information Science of Wuhan University, 2020, 45(11):1792-1800.
[40] Chen M, Tang C, Li M, et al. Changes of surface recovery at coseismic landslides and their driving factors in the Wenchuan earthquake-affected area[J]. CATENA, 2022, 210:105871.
[41] 许强. 对地质灾害隐患早期识别相关问题的认识与思考[J]. 武汉大学学报(信息科学版), 2020, 45(11):1651-1659.
[41] Xu Q. Understanding and consideration of related issues in early identification of potential geohazards[J]. Geomatics and Information Science of Wuhan University, 2020, 45(11):1651-1659.
[42] Claessens L, Heuvelink G B M, Schoorl J M, et al. DEM resolution effects on shallow landslide hazard and soil redistribution modelling[J]. Earth Surface Processes and Landforms, 2005, 30(4):461-477.
[43] Thonfeld F, Feilhauer H, Braun M, et al. Robust change vector analysis (RCVA) for multi-sensor very high resolution optical satellite data[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 50:131-140.
[44] Wang X, Wang L, Zhong X, et al. PaI-Net:A modified U-Net of reducing semantic gap for surgical instrument segmentation[J]. IET Image Processing, 2021, 15(12):2959-2969.
[45] Ding X, Guo Y, Ding G, et al. ACNet:Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul,Korea (South).IEEE, 2019:1911-1920.
[47] Denton E, Zaremba W, Bruna J, et al. Exploiting linear structure within convolutional networks for efficient evaluation[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 1.December 8 - 13,2014,Montreal,Canada.ACM, 2014:1269-1277.
[48] Jaderberg M, Vedaldi A, Zisserman A. Speeding up convolutional neural networks with low rank expansions[C]// Proceedings of the British Machine Vision Conference 2014.Nottingham.British Machine Vision Association, 2014.
[49] He K, Zhang X, Ren S, et al. Delving deep into rectifiers:Surpassing human-level performance on ImageNet classification[C]// 2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile.IEEE, 2015:1026-1034.
[1] CHEN Gang, HAO Shefeng, JIANG Bo, YU Yongxiang, CHE Zengguang, LIU Hanhu, YANG Ronghao. Identification and assessment of small landslides in densely vegetated areas based on airborne LiDAR technique[J]. Remote Sensing for Natural Resources, 2024, 36(3): 196-205.
[2] ZHANG Ruirui, XIA Lang, CHEN Liping, DING Chenchen, ZHENG Aichun, HU Xinmiao, YI Tongchuan, CHEN Meixiang, CHEN Tianen. Identifying discolored trees inflected with pine wilt disease using DSSN-based UAV remote sensing[J]. Remote Sensing for Natural Resources, 2024, 36(3): 216-224.
[3] LUO Wei, LI Xiuhua, QIN Huojuan, ZHANG Muqing, WANG Zeping, JIANG Zhuhui. Identification and yield prediction of sugarcane in the south-central part of Guangxi Zhuang Autonomous Region, China based on multi-source satellite-based remote sensing images[J]. Remote Sensing for Natural Resources, 2024, 36(3): 248-258.
[4] WU Dehong, HAO Lina, YAN Lihua, TANG Fengshun, ZHENG Guang. InSAR-based detection and deformation factor analysis of landslide clusters in the Jinsha River[J]. Remote Sensing for Natural Resources, 2024, 36(3): 259-266.
[5] WEN Quan, LI Lu, XIONG Li, DU Lei, LIU Qingjie, WEN Qi. A review of water body extraction from remote sensing images based on deep learning[J]. Remote Sensing for Natural Resources, 2024, 36(3): 57-71.
[6] ZHANG Lijun, HE Sirui, ZHANG Jiandong, PENG Guangxiong, XU Zhibin, XIE Jiancheng, TANG Kai, BU Jiancai. Identification of landslide hazards based on multi-source remote sensing technology:A case study of the Changli area in Hunan Province[J]. Remote Sensing for Natural Resources, 2024, 36(2): 173-187.
[7] YANG Fan, MA Zhigang, WEN Yan, Dong Jie, JIANG Qinghui. Monitoring a landslide with a multi-deformation magnitude based on the phase and amplitude information of SAR images: A case study of the Baige landslide in Jinsha River[J]. Remote Sensing for Natural Resources, 2024, 36(2): 257-267.
[8] SONG Shuangshuang, XIAO Kaifei, LIU Zhaohua, ZENG Zhaoliang. A YOLOv5-based target detection method using high-resolution remote sensing images[J]. Remote Sensing for Natural Resources, 2024, 36(2): 50-59.
[9] LI Wanyue, LOU Debo, WANG Chenghui, LIU Huan, ZHANG Changqing, FAN Yinglin, DU Xiaochuan. A granitic pegmatite information extraction method based on improved U-Net[J]. Remote Sensing for Natural Resources, 2024, 36(2): 89-96.
[10] CAI Jian’ao, MING Dongping, ZHAO Wenyi, LING Xiao, ZHANG Yu, ZHANG Xingxing. Integrated remote sensing-based hazard identification and disaster-causing mechanisms of landslides in Zayu County[J]. Remote Sensing for Natural Resources, 2024, 36(1): 128-136.
[11] SONG Yingxu, ZOU Yujia, YE Runqing, HE Zhixia, WANG Ningtao. Dynamic analysis of landslide hazards in the Three Gorges Reservoir area based on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2024, 36(1): 154-161.
[12] LI Xintong, SHI Lan, CHEN Duoyan. A deep learning-based study on downscaling of GPM products in Fujian-Zhejiang-Jiangxi area[J]. Remote Sensing for Natural Resources, 2023, 35(4): 105-113.
[13] YU Shaohuai, XU Qiao, YU Fei. Method for assessing landslide susceptibility of highways in mountainous areas based on optical and SAR remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(4): 81-89.
[14] DENG Dingzhu. Deep learning-based cloud detection method for multi-source satellite remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(4): 9-16.
[15] CHEN Di, PENG Qiuzhi, HUANG Peiyi, LIU Yaxuan. Detecting land for photovoltaic development based on the attention mechanism and improved YOLOv5[J]. Remote Sensing for Natural Resources, 2023, 35(4): 90-95.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech