предыдущий|следующий

Detection of earthquake-damaged buildings via UAV high-resolution remote sensing images

  • role： First author第一作者
  • Affiliation：

    Information Science and Technology, Yunnan Normal University, Kunming 650500, China

    Laboratory of Pattern Recognition and Artificial Intelligence, Yunnan Normal University, Kunming 650500, China

  • Email：whf200608@163.com
  • Introduction：王海峰，研究方向为目标检测、深度学习的理论和应用。E-mail： whf200608@163.com
WANG Haifeng12,  
  • Affiliation：

    Information Science and Technology, Yunnan Normal University, Kunming 650500, China

    Laboratory of Pattern Recognition and Artificial Intelligence, Yunnan Normal University, Kunming 650500, China

ZHOU Chengjiang12,  
  • Affiliation：

    Yunnan Province Center of Relief Material Reserve, Kunming 650300, China

CHEN Xuefeng3,  
  • role： Corresponding author通信作者
  • Affiliation：

    Information Science and Technology, Yunnan Normal University, Kunming 650500, China

    Laboratory of Pattern Recognition and Artificial Intelligence, Yunnan Normal University, Kunming 650500, China

    Physics and Electron Information, Yunnan Normal University, Kunming 650500, China

  • Email：yyang_ynu@163.com
  • Introduction：杨扬，研究方向为人工智能和模式识别。E-mail： yyang_ynu@163.com
YANG Yang124*

реферат

Natural disasters occur frequently in Yunnan, China and cause enormous losses of life and property. An object detection technology based on the deep learning of remote sensing images can be used to rapidly locate damaged buildings caused by natural disasters and subsequently aid with disaster relief. However, several challenges affect the detection of damaged buildings, such as the lack of data on earthquake-damaged buildings and the weakness of the features of objects to be detected. Thus, a UAV remote-sensing image-based largescale high-resolution earthquake-damaged building database (UEDB) was constructed. A total of 4598 remote sensing images were collected in the disaster area of Yangbi Yi Autonomous County in Dali Bai Autonomous Prefecture, Yunnan Province, China. The dataset includes 76,012 building instances, with each instance labeled in three formats: an object location box label, an object segmentation label, and an object boundary label. Then, a novel Earthquake-Damaged Buildings Real-time Detection Model (EDBRDM) was constructed. This model includes three modules: object feature alignment (OFAM), feature difference calculation (FDCM) , and object boundary constraint-based position box detection. The processing procedure of this model is as follows. Firstly, the OFAM correct the misalignment issues in images taken before and after a disaster, ensuring precise alignment of object features. This crucial step forms the foundation for subsequent feature analysis and difference calculation. Secondly, the FDCM is employed to compute the differences in features, highlighting the damage characteristics of buildings. By comparing the image features before and after the disaster, we can more clearly identify the damage of buildings, providing strong support for subsequent identification and analysis of damaged buildings. Lastly, the OBCPB introduces shallow boundary features into deep features, providing boundary constraints for the prediction of damaged building locations and categories. This step helps enhance detection accuracy, ensuring that we can accurately identify and locate damaged buildings. Through the collaborative effort of these three steps, we can achieve precise detection of damaged buildings. To validate the crucial role of the proposed modules, we delve into the internal operating principles of the model through the lens of feature visualization. Firstly, by comparing the feature changes after OFAM processing, we can clearly observe the significant improvements in the alignment of features across pre- and post-disaster images, demonstrating the effectiveness of OFAM in correcting image offsets. Secondly, by observing the enhancement of damaged building features by FDCM, we find that it effectively highlights the damaged areas of buildings, providing strong support for subsequent identification and analysis of damaged buildings. Finally, through the observation of the boundary constraint effect of OBCPB, we can see how it helps to improve the localization accuracy of the model, ensuring that damaged building objects can be accurately identified. It is noteworthy that our proposed model, EDBRDM, has achieved a remarkable accuracy of 86% on the UEDB test dataset, fully demonstrating its excellent performance. Furthermore, the application of EDBRDM to actual scenes in different locations has also yielded satisfactory results, further validating its effectiveness and reliability in practical applications.

ключеви́че слова́

deep learning;high-resolution remote sensing images;object detection;change detection;earthquake disaster

References

  1. 1.
    Aamir M, Pu Y F, Rahman Z, Tahir M, Naeem H and Dai Q. 2019. A framework for automatic building detection from low-contrast satellite images. Symmetry, 11(1): 3
  2. 2.
    Devaguptapu C, Akolekar N, Sharma M M and Balasubramanian V N. 2019. Borrow from anywhere: pseudo multi-modal object detection in thermal imagery//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Long Beach, USA: IEEE: 1029-1038
  3. 3.
    Dong Y S, Wang R and He J. 2019. Real-time network intrusion detection system based on deep learning//2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS). Beijing, China: IEEE: 1-4
  4. 4.
    Fujita S and Hatayama M. 2023. Estimation method for roof-damaged buildings from aero-photo images during earthquakes using deep learning. Information Systems Frontiers, 25(1): 351-363
  5. 5.
    Gonzalez-Drigo R, Cabrera E, Luzi G, Pujades L G, Vargas-Alzate Y F and Avila-Haro J. 2019. Assessment of post-earthquake damaged building with interferometric real aperture radar. Remote Sensing, 11(23): 2830
  6. 6.
    Gupta R, Hosfelt R, Sajeev S, Patel N, Goodman B, Doshi J, Heim E, Choset H and Gaston M. 2019. xBD: a dataset for assessing building damage from satellite imagery. arXiv preprint arXiv: 1911.09296
  7. 7.
    Ji S P, Wei S Q and Lu M. 2019. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing, 57(1): 574-586
  8. 8.
    Kampffmeyer M, Salberg A B and Jenssen R. 2016. Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Las Vegas: IEEE: 680-688 [DOI: 10.1109/CVPRW.2016.90].
  9. 9.
    Kuznetsova A, Maleva T and Soloviev V. 2020. Detecting apples in orchards using YOLOv3 and YOLOv5 in general and close-up images//17th International Symposium on Neural Networks. Cairo: Springer: 233-243
  10. 10.
    Li Q, Wang W, Wang J F, Zhang J F and Geng D. 2021. Exploring the relationship between InSAR coseismic deformation and earthquake-damaged buildings. Remote Sensing of Environment, 262: 112508
  11. 11.
    Mishra B, Garg D, Narang P and Mishra V. 2020. Drone-surveillance for search and rescue in natural disaster. Computer Communications, 156: 1-10
  12. 12.
    Nie J Y, Qu S C, Wei Y T, Zhang L M and Deng L Z. 2018. An infrared small target detection method based on multiscale local homogeneity measure. Infrared Physics and Technology, 90: 186-194
  13. 13.
    Pulvirenti L, Squicciarino G and Fiori E. 2020. A method to automatically detect changes in multitemporal spectral indices: application to natural disaster damage assessment. Remote Sensing, 12(17): 2681
  14. 14.
    Redmon J and Farhadi A. 2018. YOLOv3: an incremental improvement. arXiv preprint arXiv: 1804.02767
  15. 15.
    Ren Y, Zhu C R and Xiao S P. 2018. Small object detection in optical remote sensing images via modified faster R-CNN. Applied Sciences, 8(5): 813
  16. 16.
    Sarosa M, Muna N and Rohadi E. 2021. Detection of natural disaster victims using You Only Look Once (YOLO). IOP Conference Series: Materials Science and Engineering, 1098(3): 032076
  17. 17.
    Shen Y, Zhu S J, Yang T J N, Chen C, Pan D L, Chen J Y, Xiao L and Du Q. 2021. BDANet: multiscale convolutional neural network with cross-directional attention for building damage assessment from satellite images. IEEE Transactions on Geoscience and Remote Sensing, 60: 5402114
  18. 18.
    Wang Y, Yang Y, Wang B S, Wang T, Bu X H and Wang C Y. 2019. Building segmentation in high-resolution remote sensing image through deep neural network and conditional random fields. Journal of Remote Sensing (in Chinese), 23(6): 1194-1208
  19. 19.
    Wang Z Y, Wang L and Dai B. 2021. Strong-weak feature alignment for 3d object detection. Electronics, 10(10): 1205
  20. 20.
    Weiss M, Jacob F and Duveiller G. 2020. Remote sensing for agricultural applications: a meta-review. Remote Sensing of Environment, 236: 111402
  21. 21.
    Yamazaki Y, Premachandra C and Perea C J. 2020. Audio-Processing-Based human detection at disaster sites with unmanned aerial vehicle. IEEE Access, 8: 101398-101405
  22. 22.
    Zhang A, Liu XM, Gros A and Tiecke T. 2017. Building detection from satellite images on a global scale. arXiv preprint arXiv: 1707.08952
  23. 23.
    Zheng Z, Zhong Y F, Wang J J and Ma A L. 2020. Foreground-aware relation network for geospatial object segmentation in high spatial resolution remote sensing imagery//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA: IEEE: 4095-4104
  24. 24.
    Zheng Z, Zhong Y F, Wang J J, Ma A L and Zhang L P. 2021. Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: from natural disasters to man-made disasters. Remote Sensing of Environment, 265: 112636
  25. 25.
    Zhu X Y, Liang J W and Hauptmann A. 2021. MSNet: a multilevel instance segmentation network for natural disaster damage assessment in aerial videos//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Waikoloa, USA: IEEE: 2022-2031

Читать полностью

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