Extraction of road blockage information for the Jiuzhaigou earthquake based on a convolution neural network and very-high-resolution satellite images

  • Baolin Yang
  • Shixin WangEmail author
  • Yi Zhou
  • Futao WangEmail author
  • Qiao Hu
  • Ying Chang
  • Qing Zhao
Research Article


Road blockage information extraction from a single-phase postdisaster image is difficult because roads are narrow and easily covered by vegetation. The traditional object-oriented image analysis method is restrictive, and its detection is slow. A deep learning algorithm, i.e., the convolution neural network (CNN), is applied to rapidly extract road blockage information. An algorithm for sample generation is designed to construct a typical sample library for CNN training, and an appropriate CNN structure and a complete detection process are designed to extract road blockage information. Finally, by taking the Jiuzhaigou earthquake on August 8, 2017, as an example, experimental verification is carried out. The kappa coefficient and the F1 score of the results are 77.60% and 87.95%, respectively. The extraction of road blockages can be completed with an efficiency of 14.59 km2 per hour. The requirements for disaster emergency monitoring can be met by the accuracy and efficiency of this method, which are better than those of the traditional object-oriented method.


Convolution neural network Very-high-resolution satellite images Road blockage information Jiuzhaigou earthquake 



This study was supported by the National Key Research and Development Program of China (2016YFC0803000 and 2017YFB0504100) and the Youth Innovation Promotion Association of the Chinese Academy of Sciences (CAS) (2015129). The authors wish to thank Maxar Technologies Ltd. (DigitalGlobe,, Twenty First Century Aerospace Technology Co., Ltd. (21AT, and China Centre for Resources Satellite Data and Application (CRESDA,, for providing the satellite images, National Aeronautics and Space Administration (NASA, for providing the new global DEM (GDEM V2) data, and Environmental Systems Research Institute Inc. (ESRI, 380 New York Street, Redlands, CA 92373, USA) for providing the OSM data. The authors are grateful to the anonymous reviewers and editors for their valuable comments and suggestions that improved this manuscript.

Author contributions

Shixin Wang and Futao Wang conceived and designed the experiments, and Baolin Yang performed the experiments and wrote the paper. Yi Zhou provided crucial guidance and support throughout the study. Qiao Hu, Ying Chang and Qing Zhao analyzed the data.

Compliance with ethical standards

Conflict of interest

The authors declare no conflicts of interest.


  1. ArcGIS Editor for OSM 10.6.x Desktop. Availale online: (Jul 5, 2018)
  2. Audebert, N.; Le Saux, B.; Lefevre, S. Semantic segmentation of earth observation data using multimodal and multi-scale deep networks, proceedings of lecture notes in computer science, Taipei, Taiwan; Springer Verlag: 2017; 180–196Google Scholar
  3. Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE T Pattern Anal 39:2481–2495CrossRefGoogle Scholar
  4. Chen Z, Dou A (2018) Road damage extraction from post-earthquake uav images assisted by vector data. Proceedings ofBeijing, China; International Society for Photogrammetry and Remote Sensing:211–216Google Scholar
  5. Chen S, Ma; Y. Fan H, Xu F, Lian J (2008) Road damage assessment from high resolution satellite RemoteSensing imagery in Wenchuan earthquake. J Remot Sens 12:949–955 In ChineseGoogle Scholar
  6. Cook JA (2017) ROC curves and nonrandom data. Pattern Recogn Lett 85:35–41CrossRefGoogle Scholar
  7. Coulibaly I, Lepage R, St-Jacques M (2015) Road damage detection from high resolution satellite images based on machine learning, proceedings of IEEE 8th international workshop on the analysis of multi-temporal remote sensing images, 2015. Annecy, FranceGoogle Scholar
  8. Fan Y, Wen Q, Wang W, Wang P, Li L, Zhang P (2017) Quantifying disaster physical damage using remote sensing data—a technical work flow and case study of the 2014 Ludian earthquake in China. Int J Disaster Risk Sci 8:471–488CrossRefGoogle Scholar
  9. Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27:861–874CrossRefGoogle Scholar
  10. Foumelis M (2017) Impact of dam failure-induced flood on road network using combined remote sensing and geospatial approach. J Appl Remote Sens 11:16004CrossRefGoogle Scholar
  11. Fu C, Chen Y, Tong L, Jia M, Tan L, Ji X (2014) Road damage information extraction using high-resolution SAR imagery. Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Quebec City, QC, Canada; Institute of Electrical and Electronics Engineers Inc:1836–1838Google Scholar
  12. Gong L, An L, Liu M, Zhang J (2012) Road damage detection from high-resolution RS image. Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Munich, Germany; Institute of Electrical and Electronics Engineers Inc:990–993Google Scholar
  13. Haghighattalab A, Mohammadzadeh A, Valadan Zoej MJ, Taleai M (2010) Post-earthquake road damage assessment using region-based algorithms from high-resolution satellite images. Proceedings of SPIE - The International Society for Optical Engineering, Toulouse, France; SPIE:4993–4998Google Scholar
  14. Hand DJ, Anagnostopoulos C (2013) When is the area under the receiver operating characteristic curve an appropriate measure of classifier performance? Pattern Recogn Lett 34:492–495CrossRefGoogle Scholar
  15. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, United states; IEEE Computer Society:770–778Google Scholar
  16. Huang R, Pei X, Fan X, Zhang W, Li S, Li B (2012) The characteristics and failure mechanism of the largest landslide triggered by the Wenchuan earthquake, may 12, 2008, China. Landslides 9:131–142CrossRefGoogle Scholar
  17. Izadi M, Mohammadzadeh A, Haghighattalab A (2017) A new neuro-fuzzy approach for post-earthquake road damage assessment using GA and SVM classification from QuickBird satellite images. J Indian Soc Remote Sens 45:965–977CrossRefGoogle Scholar
  18. Kingma D, Ba JA (2014) A method for stochastic optimization. Computer ScienceGoogle Scholar
  19. Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84–90CrossRefGoogle Scholar
  20. Li P, Xu H, Song B (2015) A novel method for urban road damage detection using very high resolution satellite imagery and road map. Photogramm Eng Rem S 77:1057–1066CrossRefGoogle Scholar
  21. Liu X, Li X, Li J, Wang Q (2013) Object-oriented remote sensing image classification and road damage adaptive extraction. Proceedings of International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE), Nanjing, China; Atlantis Press:140–143Google Scholar
  22. Ma H, Lu N, Ge L, Li Q, You X, Li X (2013) Automatic road damage detection using high-resolution satellite images and road maps. Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Melbourne, VIC, Australia; Institute of Electrical and Electronics Engineers Inc:3718–3721Google Scholar
  23. Marmanis D, Schindler K, Wegner JD, Galliani S, Datcu M, Stilla U (2018) Classification with an edge: improving semantic image segmentation with boundary detection. ISPRS J Photogramm 135:158–172CrossRefGoogle Scholar
  24. Muni Kumar N, Manjula R (2019) Design of multi-layer perceptron for the diagnosis of diabetes mellitus using Keras in deep learning. Proceedings ofVijayawada, India; Springer Science and Business Media Deutschland GmbH:703–711Google Scholar
  25. OpenStreetMap, C. OpenStreetMap. Availale online: (Jul 7, 2018)
  26. Paisitkriangkrai S, Sherrah J, Janney P, Van Den Hengel A (2016) Semantic labeling of aerial and satellite imagery. IEEE J-STARS 9:2868–2881Google Scholar
  27. Qi S, Xu Q, Lan H, Zhang B, Liu J (2010) Spatial distribution analysis of landslides triggered by 2008.5.12 Wenchuan earthquake, China. Eng Geol 116:95–108CrossRefGoogle Scholar
  28. Qin QM, Ma HJ, Li J (2011) Damage detection and assessment system of roads for decision support for disaster. KEM 467-469:1144–1149CrossRefGoogle Scholar
  29. Samadzadegan F, Zarrinpanjeh N (2008) Earthquake destruction assessment of urban roads network using satellite imagery and fuzzy inference systems, proceedings of international archives of the photogrammetry. Remote Sensing and Spatial Information Sciences (ISPRS), Beijing, China; International Society for Photogrammetry and Remote Sensing:409–414Google Scholar
  30. Sghaier MO, Lepage R (2015) Road damage detection from VHR remote sensing images based on multiscale texture analysis and dempster Shafer theory. Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy; Institute of Electrical and Electronics Engineers Inc:4224–4227Google Scholar
  31. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of international conference on learning Representations-2015, Hilton, San Diego, pp 1–14Google Scholar
  32. Siyahghalati S, Saraf AK, Pradhan B, Jebur MN, Tehrany MS (2014) Rule-based semi-automated approach for the detection of landslides induced by 18 September 2011 Sikkim, Himalaya, earthquake using IRS LISS3 satellite images. Geomatics, Natural Hazards and Risk 7:326–344CrossRefGoogle Scholar
  33. Sun Q, Zhang L, Ding XL, Hu J, Li ZW, Zhu JJ (2015) Slope deformation prior to Zhouqu, China landslide from InSAR time series analysis. Remote Sens Environ 156:45–57CrossRefGoogle Scholar
  34. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, United states; IEEE Computer Society:1–9Google Scholar
  35. Tofani V, Segoni S, Agostini A, Catani F, Casagli N (2013) Technical note: use of remote sensing for landslide studies in Europe. Nat Hazards Earth Syst Sci 13:299–309CrossRefGoogle Scholar
  36. Wang Y, Wang Y, Da Y, Liu X, Li J, Huang J (2011) An object-oriented method for road damage detection from high resolution remote sensing images. Proceedings of International Conference on Geoinformatics, Shanghai, China; IEEE Computer SocietyGoogle Scholar
  37. Wang J, Qin Q, Zhao J, Ye X, Feng X, Qin X, Yang X (2015a) Knowledge-based detection and assessment of damaged roads using post-disaster high-resolution remote sensing image. Remote Sens 7:4948–4967CrossRefGoogle Scholar
  38. Wang J, Qin Q, Zhao J, Ye X, Qin X, Yang X, Wang J, Zheng X, Sun Y (2015b) A knowledge-based method for road damage detection using high-resolution remote sensing image. Proceedings of IEEE Geoscience and Remote Sensing Symposium, Milan, Italy; Institute of Electrical and Electronics Engineers Inc:3564–3567Google Scholar
  39. Wen Q, Chen S, He H, Li S, Bai R, Zhao X (2012) Application of remote sensing system of unmanned aerial vehicle in Yingjiang, Yunnan earthquake. J Nat Disaster 21:65–71 In ChineseGoogle Scholar
  40. Wixted, J.T.; Mickes, L.; Wetmore, S.A.; Gronlund, S.D.; Neuschatz, J.S. ROC Analysis in Theory and Practice. 2017, 6, 343–351CrossRefGoogle Scholar
  41. Xu C, Xu X, Dai F, Wu Z, He H, Shi F, Wu X, Xu S (2013) Application of an incomplete landslide inventory, logistic regression model and its validation for landslide susceptibility mapping related to the may 12, 2008 Wenchuan earthquake of China. Nat Hazards 68:883–900CrossRefGoogle Scholar
  42. Ya-lan L, Yong Z, Yu-huan R, Zhen-yu LI, Lei-qiu HU, Fu-qing Z, Hai-xia HE, Hong-tao MA (2008) C. Jiang highway damage monitoring and assessment for Wenchuan quake based on remote sensing and its information integration. J Remot Sens 933-941(In Chinese):12Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Institute of Remote Sensing and Digital EarthChinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations