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

doi:10.6046/zrzyyg.2021204

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(4049 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

我国是滑坡灾害频发的国家之一,近年来发生的灾难性地质灾害事件有70%以上都不在已知的地质灾害隐患点范围内,亟须通过自动高效的滑坡识别技术方法开展大规模滑坡灾害排查。为了从海量遥感影像中快速识别滑坡的位置,确定滑坡重点区,支撑后续的解译与研究,以黄土滑坡为例,基于GF-1影像与数字高程模型(digital elevation model,DEM) 数据开展滑坡识别研究。首先构建了遥感影像和DEM滑坡样本库,然后应用通道融合卷积神经网络模型对滑坡样本进行分类,最后将分类结果按照位置信息还原到遥感影像图中。实验结果表明模型的滑坡识别精度可达95.7%,召回率为100.0%。研究所用模型的网络层数较少,收敛速度快,具有更高的效率与识别精度,解决了在样本有限的情况下,从遥感影像中快速确定滑坡重点区的问题,以支撑大规模滑坡灾害排查。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杨昭颖
	韩灵怡
	郑向向
	李文吉
	冯磊
	王轶
	杨永鹏

关键词 ：卷积神经网络, 滑坡识别, 遥感分类, DEM, 黄土滑坡

Abstract：

China is one of the countries with frequent landslide disasters. In recent years. In recent years, more than 70% of the catastrophic geological hazards have occurred not within the scope of known hidden danger points of geological hazards in China. Therefore, there is an urgent need for investigating large-scale landslide disasters using automatic and efficient technologies and methods for landslide identification. To quickly identify the location of landslides from massive remote sensing images, it is necessary to determine the key areas of landslides to support subsequent interpretation and research. This study investigated loess landslide identification based on GF-1 images and digital elevation model (DEM) data. First, a database of remote sensing images and DEM landslide samples was constructed. Second, the landslide samples were classified using the channel fusion convolutional neural network model. Finally, the classification results were restored to the remote sensing images according to the location information. Experimental results showed that the model yielded landslide identification accuracy of 95.7% and a recall rate of 100.0%. The model used in this study has a small number of network layers, a high convergence speed, and higher efficiency and identification accuracy. As a result, it allows for the quick identification of key landslide areas from remote sensing images in the case of a limited number of samples, thus supporting the investigation of large-scale landslide disasters.

Key words： convolutional neural network landslide identification remote sensing classification DEM loess landslide

收稿日期: 2021-06-30 出版日期: 2022-06-20

ZTFLH:	TP751
	TP399

基金资助:自然资源部航空物理与遥感地质重点实验室课题“基于深度学习的滑坡体识别方法研究”(2020YFL26);中国地质调查局项目(DD20191006)

通讯作者: 韩灵怡

作者简介: 杨昭颖(1992-),女,硕士,工程师,研究方向为数据挖掘与人工智能。Email: zhaoyingzhaoting@163.com。

引用本文:

杨昭颖, 韩灵怡, 郑向向, 李文吉, 冯磊, 王轶, 杨永鹏. 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.
YANG Zhaoying, HAN Lingyi, ZHENG Xiangxiang, LI Wenji, FENG Lei, WANG Yi, YANG Yongpeng. Landslide identification using remote sensing images and DEM based on convolutional neural network: A case study of loess landslide. Remote Sensing for Natural Resources, 2022, 34(2): 224-230.

链接本文:

https://www.gtzyyg.com/CN/10.6046/zrzyyg.2021204 或 https://www.gtzyyg.com/CN/Y2022/V34/I2/224

Fig.1 研究区滑坡分布图

Fig.2 典型滑坡示例

Fig.3 模型结构图

Tab.1 训练与测试样本统计信息表

Fig.4 实验一训练精度与损失

Fig.5 实验二训练精度与损失

Tab.2 实验一与实验二的测试结果

Fig.6 滑坡识别结果图

[1]	许强, 董秀军, 李为乐. 基于天-空-地一体化的重大地质灾害隐患早期识别与监测预警[J]. 武汉大学学报(信息科学版), 2019, 44(7):957-966.
	Xu Q, Dong X J, Li W L. Integrated space-air-ground early detection,monitoring and warning system for potential catastrophic geohazards[J]. Geomatics and Information Science of Wuhan University, 2019, 44(7):957-966.
[2]	李松, 李亦秋, 安裕伦. 基于变化检测的滑坡灾害自动识别[J]. 遥感信息, 2010(1):27-31.
	Li S, Li Y Q, An Y L. Automatic recognition of landslides based on change detection[J]. Remote Sensing Information, 2010(1):27-31.
[3]	张帅娟. 变化检测和面向对象结合的高分辨率遥感影像滑坡体提取方法研究[D]. 成都: 西南交通大学, 2017.
	Zhang S J. Research on landslide body extraction method from high-resolution remote sensing image based on change detection and object-oriented[D]. Chengdu: Southwest Jiaotong University, 2017.
[4]	周志华, 林维芳, 许高程, 等. 基于面向对象的滑坡快速识别技术研究[J]. 安徽农业科学, 2012, 40(5):3017-3018,3071.
	Zhou Z H, Lin W F, Xu G C, et al. Research of fast landslide recognition based on object-oriented technology[J]. Journal of Abhui Agricultural Sciences, 2012, 40(5):3017-3018,3071.
[5]	丁辉, 张茂省, 朱卫红, 等. 黄土滑坡高分辨率遥感影像识别——以陕西省延安市地区为例[J]. 西北地质, 2019, 52(3):231-239.
	Ding H, Zhang M S, Zhu W H, et al. High resolution remote sensing for the identification if loess landslides:Example from Yan’an City[J]. Northwestern Geology, 2019, 52(3):231-239.
[6]	Ye C M, 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. doi: 10.1109/JSTARS.2019.2951725
[7]	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):1-21. doi: 10.3390/rs11010001
[8]	Wang H J, Zhang L M, Yin K S, et al. Landslide identification using machine learning[J]. Geoscience Frontiers, 2020, 12(1):351-364. doi: 10.1016/j.gsf.2020.02.012
[9]	巨袁臻, 许强, 金时超, 等. 使用深度学习方法实现黄土滑坡自动识别[J]. 武汉大学学报(信息科学版), 2020, 45(11):1747-1755.
	Ju Y Z, Xu Q, Jin S C, et al. Automatic object detection of loess landslide based on deep learning[J]. Geomatics and Information Science of Wuhan University, 2020, 45(11):1747-1755.
[10]	Ji S P, Yu D W, Shen C Y, et al. Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks[J]. Landslides, 2020:1-16.
[11]	Yu B, Chen F, Xu C. Landslide detection based on contour-based deep learning framework in case of national scale of Nepal in 2015[J]. Computers & Geosciences, 2020, 135:104388. doi: 10.1016/j.cageo.2019.104388
[12]	Ullo S L, Mohan A, Sebastianelli A, et al. A new Mask R-CNN-based method for improved landslide detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14:3799-810. doi: 10.1109/JSTARS.2021.3064981
[13]	Cheng L, Li J, Duan P, et al. A small attentional YOLO model for landslide detection from satellite remote sensing images[J]. Landslides, 2021, 18(8):2751-65. doi: 10.1007/s10346-021-01694-6
[14]	Catani F. Landslide detection by deep learning of non-nadiral and crowdsourced optical images[J]. Landslides, 2021, 18(3):1025-44. doi: 10.1007/s10346-020-01513-4
[15]	Hacıefendioğlu K, Demir G, Başağa H B. Landslide detection using visualization techniques for deep convolutional neural network models[J]. Natural Hazards, 2021, 109(1):329-50. doi: 10.1007/s11069-021-04838-y

[1]	朱博勤, 严召进, 谢晶, 刘宏, 宋小庆, 向喜琼. FAST型大射电望远镜选址洼地地形搜寻关键技术研究[J]. 自然资源遥感, 2023, 35(2): 80-88.
[2]	郑宗生, 刘海霞, 王振华, 卢鹏, 沈绪坤, 唐鹏飞. 改进3D-CNN的高光谱图像地物分类方法[J]. 自然资源遥感, 2023, 35(2): 105-111.
[3]	胡建文, 汪泽平, 胡佩. 基于深度学习的空谱遥感图像融合综述[J]. 自然资源遥感, 2023, 35(1): 1-14.
[4]	孙盛, 蒙芝敏, 胡忠文, 余旭. 多尺度轻量化CNN在SAR图像地物分类中的应用[J]. 自然资源遥感, 2023, 35(1): 27-34.
[5]	孔爱玲, 张承明, 李峰, 韩颖娟, 孙焕英, 杜漫飞. 基于知识引导的遥感影像融合方法[J]. 自然资源遥感, 2022, 34(2): 47-55.
[6]	马御棠, 潘浩, 周仿荣, 黄然, 赵加能, 罗继强, 刘靖, 孙浩轩, 贾伟洁, 张涛. 基于卫星影像的输电杆塔坐标校准方法[J]. 自然资源遥感, 2022, 34(2): 63-71.
[7]	廖廓, 聂磊, 杨泽宇, 张红艳, 王艳杰, 彭继达, 党皓飞, 冷伟. 基于多维卷积神经网络的多源高分辨率卫星影像茶园分类[J]. 自然资源遥感, 2022, 34(2): 152-161.
[8]	江娜, 陈超, 韩海丰. 海岸带地类统计模型中DEM空间尺度优选方法[J]. 自然资源遥感, 2022, 34(1): 34-42.
[9]	于新莉, 宋妍, 杨淼, 黄磊, 张艳杰. 结合空间约束的卷积神经网络多模型多尺度船企场景识别[J]. 自然资源遥感, 2021, 33(4): 72-81.
[10]	刘万军, 高健康, 曲海成, 姜文涛. 多尺度特征增强的遥感图像舰船目标检测[J]. 自然资源遥感, 2021, 33(3): 97-106.
[11]	刘钊, 赵桐, 廖斐凡, 李帅, 李海洋. 基于语义分割网络的高分遥感影像城市建成区提取方法研究与对比分析[J]. 国土资源遥感, 2021, 33(1): 45-53.
[12]	仇一帆, 柴登峰. 无人工标注数据的Landsat影像云检测深度学习方法[J]. 国土资源遥感, 2021, 33(1): 102-107.
[13]	卫虹宇, 赵银娣, 董霁红. 基于改进RetinaNet的冷却塔目标检测[J]. 国土资源遥感, 2020, 32(4): 68-73.
[14]	刘钊, 廖斐凡, 赵桐. 基于PSPNet的遥感影像城市建成区提取及其优化方法[J]. 国土资源遥感, 2020, 32(4): 84-89.
[15]	蔡之灵, 翁谦, 叶少珍, 简彩仁. 基于Inception-V3模型的高分遥感影像场景分类[J]. 国土资源遥感, 2020, 32(3): 80-89.

Viewed

Full text

Abstract

Cited

Shared

Discussed