Précédent|Prochain

Improved DeepLabV3+ model for landslide identification in high-resolution remote sensing images after earthquakes

  • role： First author第一作者
  • Affiliation：

    College of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China

  • Email：2021226056@chd.edu.cn
  • Introduction：赵通，研究方向为高分遥感影像处理、深度学习。E-mail： 2021226056@chd.edu.cn
ZHAO Tong1,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China

    State Key Laboratory of Geo-Information Engineering, Xi'an 710054, China

    Key Laboratory of Western China's Mineral Resource and Geological Engineering, Ministry of Education, Xi'an 710054, China

  • Email：shuangcheng369@chd.edu.cn
  • Introduction：张双成，研究方向为GNSS导航与精密定位、GNSS遥感、GNSS与InSAR灾害监测、空—天—地协同地质环境智能感知云平台及无人机LiDAR。E-mail： shuangcheng369@chd.edu.cn
ZHANG Shuangcheng123*,  
  • Affiliation：

    College of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China

    Geovis Spatial Technology Co., Ltd, Xi'an 710054, China

HE Xiaoning14,  
  • Affiliation：

    Geovis Spatial Technology Co., Ltd, Xi'an 710054, China

XUE Bowei4,  
  • Affiliation：

    College of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

ZHA Fukang15

résumé

Postearthquake emergency rescue must use the method of “deep learning+remote sensing” to identify landslides from high-resolution remote sensing images quickly after an earthquake. However, an excellent deep learning model cannot be separated from a large-scale, high-quality dataset as a support. The size of the dataset 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, a few public datasets of deep learning landslide identification are available; however, they hardly meet the task requirements of researchers who use deep learning methods to conduct landslide identification. Thus, this study uses the visual interpretation method to annotate the pixel level of GF-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 and ensure the accuracy of landslide annotation. Finally, a public deep learning landslide dataset with a spatial resolution of 2 m is established; it can be used to train deep learning semantic segmentation and target detection models. 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 dataset and basically meets the training data volume requirements of most deep learning landslide identification tasks. In addition, to recognize the boundary and detail information of landslides better and improve the accuracy of landslide recognition, this study 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 to fuse effectively the low-order and high-order feature output by the coding structure. The transposed convolution uses a learnable convolution kernel to upsample the feature map to process complex image structure and semantic information well. During model training, this study 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. This research provides robust support for the advancement of deep learning in landslide identification and offers substantial practical assistance for postearthquake emergency rescue efforts.

mots-clés

High-resolution remote sensing images;landslide data sets;deep learning;DeepLabv3+;GF-6

References

  1. 1.
    Chang K T, Chiang S H and Hsu M L. 2007. Modeling typhoon- and earthquake-induced landslides in a mountainous watershed using logistic regression. Geomorphology, 89(3/4): 335-347
  2. 2.
    Chen L C, Zhu Y K, Papandreou G, Schroff F and Adam H. 2018. Encoder-Decoder with atrous separable convolution for semantic image segmentation//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich: Springer: 833-851
  3. 3.
    Chen T, Trinder J C and Niu R Q. 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
  4. 4.
    Dai L X, Fan X M, Wang X, Fang C Y, Zou C B, Tang X C, Wei Z L, Xia M Y, Wang D and Xu Q. 2023. Coseismic landslides triggered by the 2022 Luding Ms6.8 earthquake, China. Landslides, 20(6): 1277-1292
  5. 5.
    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 (in Chinese), 12(6): 917-924
  6. 6.
    Hong H Y, Pradhan B, Jebur M N, Bui D T, 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
  7. 7.
    Ji S P, Yu D W, Shen C Y, Li W L 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
  8. 8.
    Jiang W D, Xi J B, Li Z H, Ding M T, Yang L G, Xie D S. 2023. Landslide detection and segmentation using Mask R-CNN with simulated hard samples. Geomatics and Information Science of Wuhan University, 48(12): 1931-1942
  9. 9.
    Ju Y Z, Xu Q, Jin S C, Li W L, Dong X J and Guo Q H. 2020. Automatic object detection of loess landslide based on deep learning. Geomatics and Information Science of Wuhan University, 45(11): 1747-1755
  10. 10.
    Keefer D K. 1984. Landslides caused by earthquakes. Geological Society of America Bulletin, 95 (4): 406-421
  11. 11.
    Keefer D K and Larsen M C. 2007. Assessing landslide hazards. Science, 316(5828): 1136-1138
  12. 12.
    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 (in Chinese), 23(4): 785-795
  13. 13.
    Li X J, Cheng X W, Chen W T, Chen G and Liu S W. 2015. Identification of forested landslides using LiDar data, object-based image analysis, and machine learning algorithms. Remote Sensing, 7(8): 9705-9726
  14. 14.
    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
  15. 15.
    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
  16. 16.
    Liu Y and Wu L Z. 2016. Geological disaster recognition on optical remote sensing images using deep learning. Procedia Computer Science, 91: 566-575
  17. 17.
    Mao J Q, He J, Liu G and Fu R. 2023. Landslide recognition based on improved DeepLabV3+ algorithm. Journal of Natural Disasters, 32(2): 227-234
  18. 18.
    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 (in Chinese), 21(4): 509-518
  19. 19.
    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
  20. 20.
    Stumpf A and Kerle N. 2011. Object-oriented mapping of landslides using Random Forests. Remote Sensing of Environment, 115(10): 2564-2577
  21. 21.
    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 (in Chinese), 12(6): 956-963
  22. 22.
    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
  23. 23.
    Wang Y, Wang X F and Jian J F. 2019. Remote sensing landslide recognition based on convolutional neural network. Mathematical Problems in Engineering, 2019: 8389368
  24. 24.
    Wu Q, Zhou C B, Huang F M and Yao C. 2022. Optimization of the landslide identification method based on a dual attention mechanism. Bulletin of Geological Science and Technology, 41(2): 246-253
  25. 25.
    Yang Z Y, Han L Y, Zheng X X, Li W J, Feng L, Wang Y and Yang Y P. 2022. Landslide identification using remote sensing images and DEM based on convolutional neural network: a case study of loess landslide. Remote Sensing for Natural Resources, 34(2): 224-230
  26. 26.
    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

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website