改进的DeepLabV3+模型用于震后高分遥感影像滑坡识别
Improved DeepLabV3+ model for landslide identification in high-resolution remote sensing images after earthquakes
- 2024年 页码：1-12
网络出版日期： 2024-03-07
DOI： 10.11834/jrs.20243393
扫 描 看 全 文
浏览全部资源
扫码关注微信
摘要
利用“深度学习+遥感”在高分遥感影像上快速识别滑坡，对于灾后应急救援工作的开展具有非常重要的现实意义。但目前为止，公开的深度学习滑坡识别数据集较少，难以满足相关研究人员利用深度学习方法开展滑坡识别研究的任务需求；基于此，本文使用谷歌地球影像和高分6号遥感影像制作并公开了一个样本数量达到10000+，空间分辨率为2米的深度学习滑坡数据集，用于相关学者开展研究。此外，为有效的识别滑坡，提取滑坡的边界及细节等信息，本文提出了一种改进的DeepLabV3+模型用于滑坡识别；即在DeepLabV3+模型的基础上，引入通道注意力机制特征融合模块和转置卷积来重构模型；实验结果表明，与主流算法（FCN， U-Net， SegNet， DeepLabV3+）相比，改进的DeepLabV3+模型在滑坡的边界及细节方面提取效果更好，所得结果更接近于真实标签。本文的相关代码和数据可在（
https：//github.com/ZhaoTong0203/landslides_identification_model_code.git
https://github.com/ZhaoTong0203/landslides_identification_model_code.git
）获得。
Abstract
It is of great practical significance for post-earthquake emergency rescue to use the method of "Deep learning + Remote sensing" to quickly identify landslides from high-resolution remote sensing images after the earthquake. However
an excellent deep learning model can not be separated from a large-scale
high-quality data set as a support
the size of the data set and the quality of the target category data annotation information contained in it directly affect the performance and application effect of the deep learning model. So far
there are few public data sets of deep learning landslide identification
which is difficult to meet the task requirements of relevant researchers using deep learning methods to carry out landslide identification research. Based on this
this paper uses the visual interpretation method to annotate the pixel level of Gaofen-6 remote sensing image and Google Earth image taken after the earthquake
and uses the digital elevation model and optical image data to establish a three-dimensional model to assist
in order to ensure the accuracy of landslide annotation; Finally
a public deep learning landslide dataset with spatial resolution of 2m is established
which can be used to train deep learning semantic segmentation model and target detection model. The dataset contains 11581 groups of data
among which the training set contains 9265 groups of data
the validation set contains 1158 groups of data
and the test set contains 1158 groups of data
which far exceeds the data volume of the existing public landslide data set and basically meets the training data volume requirements of most deep learning landslide identification tasks. In addition
in order to recognize the boundary and detail information of landslides better and improve the accuracy of landslide recognition
this paper proposes an improved DeepLabV3+ landslide recognition model based on DeepLabV3+ network by introducing channel attention mechanism
feature map fusion module and transposed convolution; The feature map fusion module of the channel attention mechanism is used to adjust the weight between different feature map channels in the model training process
so as to effectively fuse the low-order features and high-order features output by the coding structure; and the transposed convolution uses a learnable convolution kernel to upsample the feature map
so as to better process complex image structure and semantic information. In the process of model training
this paper uses the transfer learning method to transfer the backbone network architecture and its parameters of the ResNet50 model trained on the ImageNet dataset to the encoder structure of the DeepLabV3+ network model to accelerate the training of the model. Experimental results show that
compared with the mainstream algorithms (FCN
U-Net
SegNet
DeepLabV3+)
the improved DeepLabV3+ model has better extraction effect on the boundary and details of the landslide
and the results are closer to the real label; among them
MIOU is 87. 24%
Recall is 92. 47%
Precision is 90. 35
F1 score is 90. 87%
and Pixel Accuracy is 98. 91%. The code and data for this article are available at(
https://github.com/ZhaoTong0203/landslides_identification_model_code.git
https://github.com/ZhaoTong0203/landslides_identification_model_code.git
). This research provides robust support for the advancement of deep learning in landslide identification and offers substantial practical assistance for post-earthquake emergency rescue efforts.
关键词
高分遥感影像滑坡数据集深度学习DeepLabV3+
Keywords
High-resolution remote sensing imageslandslide data setsdeep learningDeepLabV3+
references
Chang K, Chiang S and Hsu M. 2007. Modeling typhoon- and earthquake-induced landslides in a mountainous watershed using logistic regression. Geomorphology, 89(3): 335-347 [DOI: 10.1016/j.geomorph.2006.12.011http://dx.doi.org/10.1016/j.geomorph.2006.12.011]
Chen L C, Zhu Y, Papandreou G, Schroff F and Adam H. 2018. Encoder-Decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), Cham: Springer International Publishing: 833-851 [DOI: 10.1007/978-3-030-01234-2_49http://dx.doi.org/10.1007/978-3-030-01234-2_49]
Chen T, Trinder J C and Niu R. 2017. Object-Oriented landslide mapping using ZY-3 satellite imagery, random forest and mathematical morphology, for the three-gorges reservoir, China. Remote Sensing, 9(4): 333 [DOI: 10.3390/rs9040333http://dx.doi.org/10.3390/rs9040333]
Dai L, Fan X, Wang X, Fang C, Zou C, Tang X, Wei Z, Xia M, Wang D and Xu Q. 2023. Coseismic landslides triggered by the 2022 Luding Ms6.8 earthquake, China. Landslides, 20(6): 1277-1292 [DOI: 10.1007/s10346-023-02061-3http://dx.doi.org/10.1007/s10346-023-02061-3]
Fan J R, Zhang J Q, Tian B W, Yan D and Tao H P. 2008. Investigation to the damaged farmland as a result of disasters induced by Wenchuan earthquake based on remote sensing: a case study of Tangjiashan area, Beichuan county, Sichuan province. Journal of Remote Sensing, 6: 917-924
范建容, 张建强, 田兵伟, 严冬, 陶和平. 2008. 汶川地震次生灾害毁坏耕地的遥感快速评估方法---以北川县唐家山地区为例. 遥感学报, 6: 917-924 [DOI: 10.11834/jrs.200806123http://dx.doi.org/10.11834/jrs.200806123]
Hong H, Pradhan B, Jebur M, Bui D, Xu C and Akgun A. 2016. Spatial prediction of landslide hazard at the Luxi area (China) using support vector machines. Environmental Earth Sciences, 75(1): 40 [DOI: 10.1007/s12665-015-4866-9http://dx.doi.org/10.1007/s12665-015-4866-9]
Ji S, Yu D, Shen C, Li W and Xu Q. 2020. Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks. Landslides, 17(6): 1337-1352 [DOI: 10.1007/s10346-020-01353-2http://dx.doi.org/10.1007/s10346-020-01353-2]
Ju Y Z, Xu Q, Jing S C. 2020. The deep learning method is used to realize the automatic identification of loess landslides. Geomatics and Information Science of Wuhan University, 45(11): 1747-1755
巨袁臻, 许强, 金时超等. 2020. 使用深度学习方法实现黄土滑坡自动识别. 武汉大学学报(信息科学版), 45(11): 1747-1755 [DOI: 10.13203/j.whugis20200132http://dx.doi.org/10.13203/j.whugis20200132]
Keefer D K. 1984. Landslides caused by earthquakes. Geological Society of America Bulletin, 95 (4): 406-421 [DOI: 10.1130/0016-7606(1984)952.0.CO;2http://dx.doi.org/10.1130/0016-7606(1984)952.0.CO;2]
Keefer D K and Larsen M C. 2007. Assessing landslide hazards. Science, 316 (5828): 1136-1138 [DOI: 10.1126/science.1143308http://dx.doi.org/10.1126/science.1143308]
Li Q, Zhang J F, Luo Y and Jiao Q S. 2019. Recognition of earthquake-induced landslide and spatial distribution patterns triggered by the Jiuzhaigou earthquake in August 8, 2017. Journal of Remote Sensing, 23(4): 785–795
李强, 张景发, 罗毅, 焦其松. 2019. 2017年“8.8”九寨沟地震滑坡自动识别与空间分布特征. 遥感学报, 23(4): 785–795 [DOI: 10.11834/jrs.20197345http://dx.doi.org/10.11834/jrs.20197345]
Li X, Cheng X, Chen W, Chen G and Liu S. 2015. Identification of forested landslides using LiDar data, object-based image analysis, and machine learning algorithms. Remote Sensing, 7(8): 9705-9726 [DOI: 10.3390/rs70809705http://dx.doi.org/10.3390/rs70809705]
Li Z, Li S S and Ge X Q. 2023. Transfer learning method for landslide extraction from GF-1 images after the Wenchuan earthquake. National Remote Sensing Bulletin, 27(8): 1866-1875
李震, 李山山, 葛小青. 2023. 迁移学习方法提取高分一号影像汶川地震震后滑坡. 遥感学报, 27(8): 1866-1875 [DOI: 10.11834/jrs.20211020http://dx.doi.org/10.11834/jrs.20211020]
Liu P, Wei Y M, Wang Q J, Chen Y and Xie J J. 2020. Research on post-earthquake landslide extraction algorithm based on improved U-Net model. Remote sensing, 12(5): 894 [DOI: 10.3390/rs12050894http://dx.doi.org/10.3390/rs12050894]
Liu Y and Wu L Z. 2016. Geological disaster recognition on optical remote sensing images using deep learning. Procedia Computer Science, 91: 566-575 [DOI: 10.1016/j.procs.2016.07.144http://dx.doi.org/10.1016/j.procs.2016.07.144]
Mao J Q, He J, Liu G and Fu X. 2023. Landslide identification based on improved DeepLabV3+ algorithm. Journal of Natural Disasters, 32(2): 227-234
毛佳琪, 何敬, 刘刚, 付饶. 2023. 基于改进的DeepLabV3+算法滑坡识别. 自然灾害学报, 32(2): 227-234 [DOI: 10.13577/j.jnd.2023.0224http://dx.doi.org/10.13577/j.jnd.2023.0224]
Peng L, Xu S N, Mei J J and Su F H. 2017. Earthquake-induced landslide recognition using high-resolution remote sensing images. Journal of Remote Sensing, 21(4): 509–518
彭令, 徐素宁, 梅军军, 苏凤环. 2017. 地震滑坡高分辨率遥感影像识别. 遥感学报, 21(4): 509–518 [DOI: 10.11834/jrs.20176176http://dx.doi.org/10.11834/jrs.20176176]
Sager C, Janiesch C and Zschech P. 2021. A survey of image labelling for computer vision applications. Journal of Business Analytics, 4(2): 91-110 [DOI: 10.1080/2573234X.2021.1908861http://dx.doi.org/10.1080/2573234X.2021.1908861]
Stumpf A and Kerle N. 2011. Object-oriented mapping of landslides using random forests. Remote Sensing of Environment, 115(10): 2564-2577 [DOI: 10.1016/j.rse.2011.05.013http://dx.doi.org/10.1016/j.rse.2011.05.013]
Su F H, Liu H J and Han Y S. 2008. The extraction of mountain hazard induced by Wenchuan earthquake and analysis of its distributing characteristic. Journal of Remote Sensing, 2008(6): 956-963
苏凤环, 刘洪江, 韩用顺. 2008. 汶川地震山地灾害遥感快速提取及其分布特点分析. 遥感学报, 2008(6): 956-963 [DOI: 10.11834/jrs.200806128http://dx.doi.org/10.11834/jrs.200806128]
Ullo S L, Mohan A, Sebastianelli A, Ahamed S E, Kumar B, Dwivedi R and Sinha G R. 2021. A new Mask R-CNN based method for improved landslide detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 3799-3810 [DOI: 10.1109/JSTARS.2021.3064981http://dx.doi.org/10.1109/JSTARS.2021.3064981]
Wang Y, Wang X and Jian J.2019.Remote sensing landslide recognition based on convolutional neural network. Mathematical Problems in Engineering, 2019: 1-12 [DOI: 10.1155/2019/8389368http://dx.doi.org/10.1155/2019/8389368]
Wu Q, Zhou C B, Huang F M and Yao C. 2022. Optimization of landslide recognition method based on double attention mechanism. Bulletin of Geological Science and Technology, 41(2): 246-253
吴琪, 周创兵, 黄发明, 姚池. 2022. 基于双重注意力机制的滑坡识别方法优化. 地质科技通报, 41(2): 246-253 [DOI: 10.19509/j.cnki.dzkq.2022.0053http://dx.doi.org/10.19509/j.cnki.dzkq.2022.0053]
Xi J B, Jiang W D, Li X Y, Dou X Y, Yin X G, Zhang X. 2021. Landslide segmentate on method based on simulated difficult samples with Mask-RCNN. China, CN112712535A.
席江波, 姜万冬, 李晓阳, 窦新玉, 殷晓广, 张潇. 2021. 基于模拟困难样本的Mask-RCNN滑坡分割方法. 中国, CN112712535A.
Yang Z Y, Han L Y, Zheng X X, Li W J, Feng L, Wang Y and Yang Y P. 2022. Remote sensing image and DEM landslide recognition based on convolutional neural network: a case study of loess landslide. Remote Sensing for Natural Resources, 34(2): 224-230
杨昭颖, 韩灵怡, 郑向向, 李文吉, 冯磊, 王轶, 杨永鹏. 2022. 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. 自然资源遥感, 34(2): 224-230 [DOI: 10.6046/zrzyyg.2021204http://dx.doi.org/10.6046/zrzyyg.2021204]
Zhang D, Wu Z H, Li J C and Jiang Y. 2013. An overview on earthquake-induced landslide research. Journal of Geomechanics, 19 (3): 225-241
张铎, 吴中海, 李家存, 蒋瑶. 2013. 国内外地震滑坡研究综述. 地质力学学报, 19(3): 225-241 [DOI: 10.3969/j.issn.1006-6616.2013.03.001http://dx.doi.org/10.3969/j.issn.1006-6616.2013.03.001]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
北京师范大学 地理科学学部 地表过程与资源生态国家重点实验室
北京师范大学 地理科学学部 北京市陆表遥感数据产品工程技术研究中心
北京林业大学 信息学院
国家林业和草原局林业智能信息处理工程技术研究中心
南京信息工程大学 遥感与测绘工程学院
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部