Submitted Successfully!
To reward your contribution, here is a gift for you: A free trial for our video production service.
Thank you for your contribution! You can also upload a video entry or images related to this topic.
Version Summary Created by Modification Content Size Created at Operation
1
Ali Mohammadzadeh
 -- 1843 2024-01-10 12:08:10 |
2 layout & references
Sirius Huang
 Meta information modification 1843 2024-01-11 02:19:27 |

Video Upload Options

Do you have a full video?
Send video materials Upload full video

Confirm

Are you sure to Delete?
Yes No
Cite
If you have any further questions, please contact Encyclopedia Editorial Office.
Ahmadi, S.A.; Mohammadzadeh, A.; Yokoya, N.; Ghorbanian, A. Building Damage Assessment using Remote Sensing Satellite Images. Encyclopedia. Available online: https://encyclopedia.pub/entry/53680 (accessed on 01 July 2024).
Ahmadi SA, Mohammadzadeh A, Yokoya N, Ghorbanian A. Building Damage Assessment using Remote Sensing Satellite Images. Encyclopedia. Available at: https://encyclopedia.pub/entry/53680. Accessed July 01, 2024.
Ahmadi, Seyed Ali, Ali Mohammadzadeh, Naoto Yokoya, Arsalan Ghorbanian. "Building Damage Assessment using Remote Sensing Satellite Images" Encyclopedia, https://encyclopedia.pub/entry/53680 (accessed July 01, 2024).
Ahmadi, S.A., Mohammadzadeh, A., Yokoya, N., & Ghorbanian, A. (2024, January 10). Building Damage Assessment using Remote Sensing Satellite Images. In Encyclopedia. https://encyclopedia.pub/entry/53680
Ahmadi, Seyed Ali, et al. "Building Damage Assessment using Remote Sensing Satellite Images." Encyclopedia. Web. 10 January, 2024.
Building Damage Assessment using Remote Sensing Satellite Images
Edit
This entry is adapted from the peer-reviewed paper 10.3390/rs16010182

When natural disasters occur, timely and accurate building damage assessment maps are vital for disaster management responders to organize their resources efficiently. Pairs of pre- and post-disaster remote sensing imagery have been recognized as invaluable data sources that provide useful information for building damage identification. 

natural disaster damage mapping deep learning selective kernel building damage assessment

1. Introduction

Annually, thousands of people worldwide lose their lives due to damages caused by natural disasters [1][2][3]. Countries spend millions of dollars on rebuilding infrastructures and compensating for the associated damages. Accordingly, providing accurate building damage assessment maps, with the location, number, and severity of damages, is critical for emergency responders and relevant organizations to manage their resources appropriately [4].
Remote sensing images are capable of providing overviews from large regions of the affected area for faster building damage assessment. Remote sensing data, i.e., satellite images, drone/aerial imagery, or Synthetic Aperture Radar (SAR) data, have proven their applicability in providing useful information for disaster management. Although SAR sensors propose all-weather data availability [5][6], or drone imagery obtains higher spatial resolutions [7][8], satellite optical images are more cost-effective with respect to the coverage area. They can be obtained in near-real-time thanks to the numerous satellites and constellations in orbit, and thus, are one of the best choices to rely on during disaster conditions [9]. In summary, key attributes of optical satellite images are their wide area coverage, rapid revisits, simple interpretation, and fast deployment [9].
According to the temporal usage of satellite images for building damage assessment, the current literature can be divided into two categories: (1) techniques that only use post-disaster images and (2) techniques that are based on both pre- and post-disaster images. For the first group, which relies on post-disaster images, the task of damage assessment is mainly considered to be a semantic segmentation problem [10][11][12][13]. However, without using pre-disaster images, post-disaster images are not appropriate sources for precise extraction of building footprints [14]. Additionally, researchers require auxiliary information, such as pre-disaster building masks obtained from external resources, e.g., municipality databases or OpenStreetMap, to enhance their results [15][16]. On the other hand, having both pre- and post-disaster satellite images from the affected region will help locate the buildings and assess their damaged parts.
It is worth mentioning that the problem of building damage assessment using both pre- and post-disaster satellite images is inherently very similar to a change detection problem. In both scenarios, pre- and post-disaster images are compared with each other to find changes [17][18]. The main difference, making damage assessment a more complicated problem, is that in change detection, only changed objects (e.g., buildings) are detected, and everything else is ignored. In contrast, both changed (damaged) and unchanged (not-damaged) buildings should be found in the building damage assessment. Another difference is the requirement to classify different damage categories, which implies a multi-class change detection problem [14][19].
From another point of view, according to the utilized processing techniques, building damage assessment has been addressed by (1) visual interpretation of images, (2) machine learning-based methods relying on hand-crafted features, and (3) deep learning techniques. Traditionally, satellite images were visually interpreted by researchers and experts to obtain estimations of the amount of damage over the affected area [20]. Even with large groups of experts and interpreters, visual investigation of remote sensing images for building damage assessment is not a time- and cost-efficient procedure. Therefore, automatic techniques were introduced to process remote sensing images for building extraction and damage assessment. Based on the human experience obtained from visual interpretations, machine learning techniques with very few trainable parameters, which relied on hand-crafted features, such as textural, spectral, and spatial features, were developed [21][22][23][24]. In addition to the amount of time and experience required for feature extraction, manually extracted features were not generalizable to other geographical regions, and in most cases, they were valid for specific conditions [25].
Recently, deep learning models, primarily based on Convolutional Neural Networks (CNNs), have shown great success in various computer vision tasks such as classification or semantic segmentation [26][27][28]. These models are well-suited for such applications due to their ability to automatically learn hierarchical representations of low- to high-level features from raw images. Many studies leveraged deep learning methods to tackle the task of building damage assessment and achieved noteworthy developments [15][29][30][31]. For instance, Abdi et al. [32] classified building patches into four levels of damage by employing CNNs on post-hurricane Unmanned Aerial Vehicle (UAV) images. Likewise, Zhang et al. [33] used bi-temporal images acquired before and after disasters to develop an end-to-end procedure for solving a semantic segmentation problem with the aim of building damage assessment.
Using pre- and post-disaster images is an approved way for building damage assessment. The key question is how to exploit the required information from these images to ensure efficient performance. Inspired by the Siamese-network concepts introduced by Zhan et al. and Daudt et al. in [17][18], two-branch CNN architectures were used in building damage assessment using bi-temporal satellite images. Moreover, researchers utilized various types of feature fusion schemes to address this problem. For instance, Duarte et al. [30] conducted experiments on multiple feature concatenation strategies for building façade damage detection. In another study, Mei et al. [34] developed a dual-temporal aggregation module to capture global change patterns and performed a difference-aware fusion technique to assess building damages. Based on the powerful properties of attention-mechanism-enabled networks, which focus on more important regions of the images [35], Shen et al. [36] introduced a cross-directional attention module to explore the spatial and channel-wise correlations between pre- and post-disaster images.

2. Building Damage Assessment using Remote Sensing Satellite Images

This section discusses the methods that recently were used for building damage assessment using remote sensing satellite images. Due to the high impact of natural disasters on human lives, it has always been a hot topic to study various techniques to cope with the damages that occur to cities. Many researchers from two decades ago have started to use satellite images for the purpose of building damage assessment [6][20][37]. In the meantime, researchers have developed more sophisticated methods based on machine learning techniques to automate the assessment process [9][25][38]. As an example, Putri et al. [25] tried to generate building damage assessment maps using textural and spectral features extracted from pre- and post-disaster Sentinel-1 and Sentinel-2 images. They fed the features into a Random Forest classifier for classification. Alatas et al. [39] compared different morphological profiles with Haralick’s texture features to detect damaged buildings using a k-Nearest Neighbor classifier. Likewise, Janalipour et al. [40] utilized an ANFIS-based decision-making system powered by geometrical features and bi-temporal satellite images combined with building vector maps to detect damaged buildings in the Bam earthquake.
Recently, deep learning techniques have been widely studied to provide more general solutions for the task of building damage assessment [19][36]. The ability of deep learning models to provide high-dimensional representations of images has enabled them to solve more sophisticated challenges. For instance, Zheng et al. utilized a deep object-based semantic change detection method to evaluate damages to buildings that occurred due to natural and man-made disasters [19]. In [41], Wu et al. proposed a variety of attention UNets to localize and classify building damages. By detecting changes in super-pixels, Qing et al. [14] proposed a CNN-based network for damage assessment using UAV images. Moreover, in [12], Deng et al. proposed a two-stage UNet supplemented with the Squeeze and Excitation (SE) module to improve the damage assessment results.
According to the usage of only post-disaster images [11][32][42] or the pair of pre- and post-disaster images [12][34][36], various methodologies have been proposed for building damage assessment. In [29], Duarte et al. proposed various fusion strategies for building damage assessment from post-disaster satellite, aerial, or UAV images using CNNs. In [15], Tilon et al. proposed an unsupervised method for building damage assessment. However, without any guidance from pre-disaster images or possible external sources of building footprint maps such as OpenStreetMap [15], post-disaster images cannot provide precise building boundaries [14]. In this regard, in 2013, Dong et al. [9] showed that most of the studies tend to use pairs of pre- and post-disaster images to be able to locate the damaged building and evaluate the damage by detecting meaningful changes. Accordingly, Khodaverdizahraee et al. [43] extracted building properties such as shape, geometry, shadow, texture, and color from pre- and post-disaster imagery and fed them into machine learning algorithms for improved building damage assessment. Likewise, Xu et al. [44] compared different pre- and post-disaster feature fusion scenarios in CNN models for the Haiti earthquake.
From the architecture’s point of view in deep learning methodologies, various architectures from the computer vision community have been proposed for building damage assessment. Inspired by atrous spatial pyramid pooling networks, with dilated convolutions, Gupta et al. [45] proposed a network (RescueNet) with multiple segmentation heads for simultaneous building detection and damage classification. Valentijn et al. [46] studied the effective parameters of damage assessment predictions by using simple, fully connected CNNs. Compared with other architectures, UNets, with encoder-decoder paths that were improved by adding skip-connections to aggregate low-level and high-level features, have been widely used for the task of building damage assessment [12][36][41].
In order to improve the performance of baseline semantic segmentation architectures, researchers have used various strategies and extensions in their networks. For instance, Bai et al. [47] used a lightweight approach based on knowledge distillation to reduce the dependence on computing resources and increase the speed of damage assessment in emergency situations. In contrast, in order to achieve more accurate results with fewer labels, Qiao et al. [48] implemented a weakly supervised technique that could improve the quality of activation maps and boost model performance. Attention techniques [34][48], which try to emphasize important regions of the images, have been widely used in computer vision tasks. Mei et al. [34] used a difference-aware attention strategy to predict more accurate localization and classification results after disasters. For a superior combination of features in spatial and channel directions, Shen et al. [36] proposed BDANet with a cross-directional attention mechanism and obtained enhanced damage assessment maps. Attention-based mechanisms have shown promising results in both computer vision and building damage assessment.
From the development point of view, appropriate and carefully annotated datasets play a major role in deep learning models. Deep learning models are data-hungry, and the issue is exacerbated by the complexity of the problem [49]. Building damage assessment is a complicated problem and, thus, requires large amounts of ground truth data for model development. Preparing annotated remote sensing images for such tasks is time-consuming and requires huge manual work. Although the number of benchmark datasets is growing in the remote sensing community, high-quality datasets that are suitable for building damage classification are still rare [50]. The xBD dataset [51] has played a game-changing role in building damage assessment during the past five years. However, it still has some challenges, such as highly biased classes towards no-damage buildings. Furthermore, complexities of minor-damage and major-damage classes, besides similarities between minor-damage and no-damage classes, lead to moderate misclassification [52]. Preprocessing techniques such as data augmentation have been widely utilized to increase the size of data and robustness of the model [53]. They can also act like regularization techniques that feed models with more challenging scenarios [53][54]. Advanced augmentation methods, such as the Cutout, randomly mask out square regions of input images to improve the feature representation ability of the model [55].

References

  1. Ritchie, H.; Roser, M. Natural Disasters. Our World in Data. Available online: https://ourworldindata.org/natural-disasters (accessed on 27 April 2023).
  2. Ji, M.; Liu, L.; Zhang, R.; Buchroithner, M.F. Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model. Appl. Sci. 2020, 10, 602.
  3. Marjani, M.; Ahmadi, S.A.; Mahdianpari, M. FirePred: A Hybrid Multi-Temporal Convolutional Neural Network Model for Wildfire Spread Prediction. Ecol. Inform. 2023, 78, 102282.
  4. Matin, S.S.; Pradhan, B. Challenges and Limitations of Earthquake-Induced Building Damage Mapping Techniques Using Remote Sensing Images-A Systematic Review. Geocarto Int. 2021, 37, 6186–6212.
  5. Cho, S.; Xiu, H.; Matsuoka, M. Backscattering Characteristics of SAR Images in Damaged Buildings Due to the 2016 Kumamoto Earthquake. Remote Sens. 2023, 15, 2181.
  6. Chini, M.; Pierdicca, N.; Emery, W.J. Exploiting SAR and VHR Optical Images to Quantify Damage Caused by the 2003 Bam Earthquake. IEEE Trans. Geosci. Remote Sens. 2008, 47, 145–152.
  7. Kerle, N.; Nex, F.; Gerke, M.; Duarte, D.; Vetrivel, A. UAV-Based Structural Damage Mapping: A Review. ISPRS Int. J. Geo-Inf. 2019, 9, 14.
  8. Ghaffarian, S.; Kerle, N. Towards Post-Disaster Debris Identification for Precise Damage and Recovery Assessments from Uav and Satellite Images. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. ISPRS Arch. 2019, 42, 297–302.
  9. Dong, L.; Shan, J. A Comprehensive Review of Earthquake-Induced Building Damage Detection with Remote Sensing Techniques. ISPRS J. Photogramm. Remote Sens. 2013, 84, 85–99.
  10. Cao, Q.D.; Choe, Y. Building Damage Annotation on Post-Hurricane Satellite Imagery Based on Convolutional Neural Networks. Nat. Hazards 2020, 103, 3357–3376.
  11. Lin, C.; Li, Y.; Liu, Y.; Wang, X.; Geng, S. Building Damage Assessment from Post-Hurricane Imageries Using Unsupervised Domain Adaptation with Enhanced Feature Discrimination. IEEE Trans. Geosci. Remote Sens. 2021, 60, 4700310.
  12. Deng, L.; Wang, Y. Post-Disaster Building Damage Assessment Based on Improved U-Net. Sci. Rep. 2022, 12, 15862.
  13. McNamara, D.; Mell, W.; Maranghides, A. Object-Based Post-Fire Aerial Image Classification for Building Damage, Destruction and Defensive Actions at the 2012 Colorado Waldo Canyon Fire. Int. J. Wildland Fire 2020, 29, 174–189.
  14. Qing, Y.; Ming, D.; Wen, Q.; Weng, Q.; Xu, L.; Chen, Y.; Zhang, Y.; Zeng, B. Operational Earthquake-Induced Building Damage Assessment Using CNN-Based Direct Remote Sensing Change Detection on Superpixel Level. Int. J. Appl. Earth Obs. Geoinf. 2022, 112, 102899.
  15. Tilon, S.; Nex, F.; Kerle, N.; Vosselman, G. Post-Disaster Building Damage Detection from Earth Observation Imagery Using Unsupervised and Transferable Anomaly Detecting Generative Adversarial Networks. Remote Sens. 2020, 12, 4193.
  16. Ghaffarian, S.; Kerle, N.; Pasolli, E.; Jokar Arsanjani, J. Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data. Remote Sens. 2019, 11, 2427.
  17. Zhan, Y.; Member, S.; Fu, K.; Yan, M.; Sun, X.; Wang, H.; Qiu, X. Change Detection Based on Deep Siamese Convolutional Network for Optical Aerial Images. IEEE Geosci. Remote Sens. Lett. 2017, 14, 1845–1849.
  18. Daudt, R.C.; Le Saux, B.; Boulch, A. Fully Convolutional Siamese Networks for Change Detection. In Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, 7–10 October 2018; pp. 4063–4067.
  19. Zheng, Z.; Zhong, Y.; Wang, J.; Ma, A.; Zhang, L. Building Damage Assessment for Rapid Disaster Response with a Deep Object-Based Semantic Change Detection Framework: From Natural Disasters to Man-Made Disasters. Remote Sens. Environ. 2021, 265, 112636.
  20. Yamazaki, F.; Yano, Y.; Matsuoka, M. Visual Damage Interpretation of Buildings in Bam City Using QuickBird Images Following the 2003 Bam, Iran, Earthquake. Earthq. Spectra 2005, 21, 329–336.
  21. Sheykhmousa, M.; Mahdianpari, M.; Ghanbari, H.; Mohammadimanesh, F.; Ghamisi, P.; Homayouni, S. Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 6308–6325.
  22. Janalipour, M.; Taleai, M. Building Change Detection after Earthquake Using Multi-Criteria Decision Analysis Based on Extracted Information from High Spatial Resolution Satellite Images. Int. J. Remote Sens. 2017, 38, 82–99.
  23. Janalipour, M.; Mohammadzadeh, A. A Novel and Automatic Framework for Producing Building Damage Map Using Post-Event LiDAR Data. Int. J. Disaster Risk Reduct. 2019, 39, 101238.
  24. Kakooei, M.; Ghorbanian, A.; Baleghi, Y.; Amani, M.; Nascetti, A. Remote Sensing Technology for Postdisaster Building Damage Assessment. In Computers in Earth and Environmental Sciences; Elsevier: Amsterdam, The Netherlands, 2022; pp. 509–521.
  25. Putri, A.F.S.; Widyatmanti, W.; Umarhadi, D.A. Sentinel-1 and Sentinel-2 Data Fusion to Distinguish Building Damage Level of the 2018 Lombok Earthquake. Remote Sens. Appl. 2022, 26, 100724.
  26. Hoeser, T.; Kuenzer, C. Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends. Remote Sens. 2020, 12, 1667.
  27. Audebert, N.; Le Saux, B.; Lefevre, S. Deep Learning for Classification of Hyperspectral Data: A Comparative Review. IEEE Geosci. Remote Sens. Mag. 2019, 7, 159–173.
  28. Khelifi, L.; Mignotte, M. Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis. IEEE Access 2020, 8, 126385–126400.
  29. Duarte, D.; Nex, F.; Kerle, N.; Vosselman, G. Multi-Resolution Feature Fusion for Image Classification of Building Damages with Convolutional Neural Networks. Remote Sens. 2018, 10, 1636.
  30. Duarte, D.; Nex, F.; Kerle, N.; Vosselman, G. Detection of Seismic Façade Damages with Multi-Temporal Oblique Aerial Imagery. GIsci. Remote Sens. 2020, 57, 670–686.
  31. Nex, F.; Duarte, D.; Tonolo, F.G.; Kerle, N. Structural Building Damage Detection with Deep Learning: Assessment of a State-of-the-Art CNN in Operational Conditions. Remote Sens. 2019, 11, 2765.
  32. Abdi, G.; Esfandiari, M.; Jabari, S. A Deep Transfer Learning-Based Damage Assessment on Post-Event Very High-Resolution Orthophotos. Geomatica 2022, 75, 237–250.
  33. Zhang, Y.; Yang, G.; Gao, A.; Lv, W.; Xie, R.; Huang, M.; Liu, S. An Efficient Change Detection Method for Disaster-Affected Buildings Based on a Lightweight Residual Block in High-Resolution Remote Sensing Images. Int. J. Remote Sens. 2023, 44, 2959–2981.
  34. Mei, J.; Zheng, Y.-B.; Cheng, M.-M. D2ANet: Difference-Aware Attention Network for Multi-Level Change Detection from Satellite Imagery. Comput. Vis. Media 2023, 9, 563–579.
  35. Oktay, O.; Schlemper, J.; Le Folgoc, L.; Lee, M.; Heinrich, M.; Misawa, K.; Mori, K.; McDonagh, S.; Hammerla, N.Y.; Kainz, B.; et al. Attention U-Net: Learning Where to Look for the Pancreas. arXiv 2018, arXiv:1804.03999.
  36. Shen, Y.; Zhu, S.; Yang, T.; Chen, C.; Pan, D.; Chen, J.; Xiao, L.; Du, Q. Bdanet: Multiscale Convolutional Neural Network with Cross-Directional Attention for Building Damage Assessment from Satellite Images. IEEE Trans. Geosci. Remote Sens. 2021, 60, 5402114.
  37. Rathje, E.M.; Crawford, M.; Woo, K.; Neuenschwander, A. Damage Patterns from Satellite Images of the 2003 Bam, Iran, Earthquake. Earthq. Spectra 2005, 21, 295–307.
  38. Kakooei, M.; Baleghi, Y. Fusion of Vertical and Oblique Images Using Intra-Cluster-Classification for Building Damage Assessment. Comput. Electr. Eng. 2023, 105, 108536.
  39. Alatas, E.O.; Taskin, G. Attribute Profiles in Earthquake Damage Identification from Very High Resolution Post Event Image. In Proceedings of the IGARSS 2019–2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 28 July–2 August 2019; pp. 9299–9302.
  40. Janalipour, M.; Mohammadzadeh, A. Building Damage Detection Using Object-Based Image Analysis and ANFIS from High-Resolution Image (Case Study: BAM Earthquake, Iran). IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2015, 9, 1937–1945.
  41. Wu, C.; Zhang, F.; Xia, J.; Xu, Y.; Li, G.; Xie, J.; Du, Z.; Liu, R. Building Damage Detection Using U-Net with Attention Mechanism from Pre-and Post-Disaster Remote Sensing Datasets. Remote Sens. 2021, 13, 905.
  42. Xie, Y.; Feng, D.; Chen, H.; Liu, Z.; Mao, W.; Zhu, J.; Hu, Y.; Baik, S.W. Damaged Building Detection from Post-Earthquake Remote Sensing Imagery Considering Heterogeneity Characteristics. IEEE Trans. Geosci. Remote Sens. 2022, 60, 4708417.
  43. Khodaverdizahraee, N.; Rastiveis, H.; Jouybari, A. Segment-by-Segment Comparison Technique for Earthquake-Induced Building Damage Map Generation Using Satellite Imagery. Int. J. Disaster Risk Reduct. 2020, 46, 101505.
  44. Xu, J.Z.; Lu, W.; Li, Z.; Khaitan, P.; Zaytseva, V. Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks. arXiv 2019, arXiv:1910.06444.
  45. Gupta, R.; Shah, M. RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery. arXiv 2020, arXiv:2004.07312.
  46. Valentijn, T.; Margutti, J.; van den Homberg, M.; Laaksonen, J. Multi-Hazard and Spatial Transferability of a CNN for Automated Building Damage Assessment. Remote Sens. 2020, 12, 2839.
  47. Bai, Y.; Su, J.; Zou, Y.; Adriano, B. Knowledge Distillation Based Lightweight Building Damage Assessment Using Satellite Imagery of Natural Disasters. Geoinformatica 2023, 27, 237–261.
  48. Qiao, W.; Shen, L.; Wang, J.; Yang, X.; Li, Z. A Weakly Supervised Semantic Segmentation Approach for Damaged Building Extraction from Postearthquake High-Resolution Remote-Sensing Images. IEEE Geosci. Remote Sens. Lett. 2023, 20, 6002705.
  49. Schmitt, M.; Ahmadi, S.A.; Hänsch, R. There Is No Data like More Data-Current Status of Machine Learning Datasets in Remote Sensing. In Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium, 11–16 July 2021; pp. 1206–1209.
  50. Schmitt, M.; Ahmadi, S.A.; Xu, Y.; Taşkin, G.; Verma, U.; Sica, F.; Hänsch, R. There Are No Data Like More Data: Datasets for Deep Learning in Earth Observation. IEEE Geosci. Remote Sens. Mag. 2023, 11, 63–97.
  51. Gupta, R.; Goodman, B.; Patel, N.; Hosfelt, R.; Sajeev, S.; Heim, E.; Doshi, J.; Lucas, K.; Choset, H.; Gaston, M. Creating XBD: A Dataset for Assessing Building Damage from Satellite Imagery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA, 16–17 June 2019; pp. 10–17.
  52. Da, Y.; Ji, Z.; Zhou, Y. Building Damage Assessment Based on Siamese Hierarchical Transformer Framework. Mathematics 2022, 10, 1898.
  53. Takahashi, R.; Matsubara, T.; Uehara, K. Data Augmentation Using Random Image Cropping and Patching for Deep CNNs. IEEE Trans. Circuits Syst. Video Technol. 2018, 30, 2917–2931.
  54. Buslaev, A.; Iglovikov, V.I.; Khvedchenya, E.; Parinov, A.; Druzhinin, M.; Kalinin, A.A. Albumentations: Fast and Flexible Image Augmentations. Information 2020, 11, 125.
  55. DeVries, T.; Taylor, G.W. Improved Regularization of Convolutional Neural Networks with Cutout. arXiv 2017, arXiv:1708.04552.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
Upload a video for this entry
Information
Subjects: Remote Sensing
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register :
Seyed Ali Ahmadi
,
Ali Mohammadzadeh
,
Naoto Yokoya
,
Arsalan Ghorbanian
View Times: 219
Revisions: 2 times (View History)
Update Date: 11 Jan 2024
Table of Contents
    1000/1000
    Hot Most Recent
    Video Production Service
    Feedback