Improving emergency response during hurricane season using computer vision

Bosch, Marc; Conroy, Christian; Ortiz, Benjamin; Bogden, Philip

doi:10.1117/12.2574639

Cited by 5 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this part, we investigate the contribution of data augmentation methods, considering whether the proposed data augmentation method is beneficial for improving the accuracy of building damage assessment. To this end, we adopt the classical building damage assessment Siamese-UNet [33] as the evaluation model, which is widely used in building damage assessment based on the xBD data set [3,34,35]. The code of the assessment model (Siamese-UNet) has been released at https://github.com/TungBui-wolf/ xView2-Building-Damage-Assessment-using-satellite-imagery-of-natural-disasters, last accessed date: 21 October 2021).…”

Section: Discussionmentioning

confidence: 99%

DisasterGAN: Generative Adversarial Networks for Remote Sensing Disaster Image Generation

et al. 2021

View full text Add to dashboard Cite

Rapid progress on disaster detection and assessment has been achieved with the development of deep-learning techniques and the wide applications of remote sensing images. However, it is still a great challenge to train an accurate and robust disaster detection network due to the class imbalance of existing data sets and the lack of training data. This paper aims at synthesizing disaster remote sensing images with multiple disaster types and different building damage with generative adversarial networks (GANs), making up for the shortcomings of the existing data sets. However, existing models are inefficient in multi-disaster image translation due to the diversity of disaster and inevitably change building-irrelevant regions caused by directly operating on the whole image. Thus, we propose two models: disaster translation GAN can generate disaster images for multiple disaster types using only a single model, which uses an attribute to represent disaster types and a reconstruction process to further ensure the effect of the generator; damaged building generation GAN is a mask-guided image generation model, which can only alter the attribute-specific region while keeping the attribute-irrelevant region unchanged. Qualitative and quantitative experiments demonstrate the validity of the proposed methods. Further experimental results on the damaged building assessment model show the effectiveness of the proposed models and the superiority compared with other data augmentation methods.

show abstract

Section: Discussionmentioning

confidence: 99%

DisasterGAN: Generative Adversarial Networks for Remote Sensing Disaster Image Generation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The HAND method is frequently used to predict flood inundation extents (Hu and Demir, 2021;Li et al, 2022) to support flood mitigation and impact analysis (Alabbad et al, 2021;Yildirim and Demir, 2022). HAND has been applied as a standalone flood mapping approach (Chaudhuri et al, 2021;Li and Demir, 2022a;Li et al, 2023), a supplementary dataset to refine the flood extent extracted from remotely sensed images (Zeng et al, 2020;He et al, 2021;Li and Demir, 2022b), and an independent data layer in flood extent extraction with machine learning approaches (Aristizabal et al, 2020;Bosch et al, 2020;Esfandiari et al, 2020;Liu et al, 2020). The HAND layer comes from the 10 m HAND dataset for the continental United States (CONUS) created by Liu et al, (2016) and is organized by HUC6 basins.…”

Section: Methodsmentioning

confidence: 99%

MA-SARNet: A one-shot nowcasting framework for SAR image prediction with physical driving forces

Li¹,

Xiang²,

Demiray³

et al. 2023

Preprint

View full text Add to dashboard Cite

Remote sensing imagery is one of the most widely used data sources for large-scale earth observations with consistent spatial and temporal quality. However, the current usage scenarios of remote sensing images are largely limited to retrospective tasks as they can only capture existing phenomena. This study proposes MA-SARNet, a one-shot forecasting framework built with a modified MA-Net structure and ResNet50 as the backbone, to predict the backscatter values of Synthetic-Aperture Radar (SAR) images using the previous observations, meteorological, and geomorphic data layers as input. The model was trained, validated, and tested with SAR images collected during the catastrophic 2019 Midwest U.S. Floods that affected several states on the Missouri and Mississippi River tributaries. Compared to the benchmark performance, model predictions show an increase of 31.9% and 17.8% for the mean and median AAI (Assemble Accuracy Index) and an increase of 37.9% and 15.1% for the mean and median NSE (Nash-Sutcliffe Efficiency) on the test set. Results showed that the flood extent derived from backscatter predictions is more robust against misclassifications caused by pixel-level noise compared to the flood map derived using the real backscatters and those from two additional flood map repositories. Results from spatial and temporal robustness tests demonstrate that the model has sufficient generalization potential for real-time, physically informed, deep learning-based earth surface prediction tasks to facilitate fast response to and mitigation for future floods.

show abstract

“…SAR imagery is popular for hydro-science applications where cloud pollution is common, for it is external illumination independent and can see through clouds (Yang et al 2020, Kong et al 2022, Li et al 2022a. Thanks to the advancement of data-driven methods, especially novel deep learning (DL) techniques, scientists can now extract useful information from SAR images with powerful data models in various tasks such as flood extent mapping (Aristizabal et al 2020, Bosch et al 2020, Li and Demir 2023, Li et al 2022b, wetland delineation (Salehi et al 2018), surface change monitoring and detection (Zhang et al 2020, Kseňak et al 2022), andobject (e.g., ship) detection (Yang et al 2020). The improved availability of SAR imagery will further facilitate advancements in those subdivisions and aspects.…”

Section: Introductionmentioning

confidence: 99%

Better Localized Predictions with Out-of-Scope Information and Explainable AI: One-Shot SAR Backscatter Nowcast Framework with Data from Neighboring Region

Li¹,

Demir²

2023

Preprint

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) provides 10-m weather-independent global Earth surface observations for various tasks such as land cover land use mapping, water body delineation, and vegetation change monitoring. However, the application of SAR imagery has been limited to retrospective tasks by a “first event then observation” rule. Recent studies have proven the feasibility of a one-shot forecast of backscatters of SAR imagery using meteorological driving forces, soil moisture, geomorphic factors, and previous SAR images collected for the target area. Although the approach is promising, spatial connectivity, more specifically, the influence of the status of surrounding areas on the target location has yet to be considered. To fill that gap, this study proposed two nowcasting frameworks that can integrate precipitation and soil moisture data collected from surrounding areas through spatial aggregation (SA) and by processing spatial series (SS), respectively. The catastrophic 2019 Central US Flooding was used as a case study with the goal of predicting backscatters of SAR imagery captured during the event. The results from SA, SS, and a framework that only considers localized input (S0) are compared against each other as well as with the benchmark performance created with persistence assumption. Results show that S0, SA, and SS outperform the benchmark. In addition, considering data from neighboring areas that contribute to the target location further improves prediction accuracy. Comparing the gradients of results considering/not considering additional data indicates that neighboring data can alter the model’s attention on each feature of the localized input matrix. The difference in gradients between SA and SS indicates the way the neighboring information is integrated also matters. The methodology proposed by this study can serve as a building block for more active usage of SAR imagery in forward-looking tasks such as early flood warning and response.

show abstract

Improving emergency response during hurricane season using computer vision

Cited by 5 publications

References 9 publications

DisasterGAN: Generative Adversarial Networks for Remote Sensing Disaster Image Generation

DisasterGAN: Generative Adversarial Networks for Remote Sensing Disaster Image Generation

MA-SARNet: A one-shot nowcasting framework for SAR image prediction with physical driving forces

Better Localized Predictions with Out-of-Scope Information and Explainable AI: One-Shot SAR Backscatter Nowcast Framework with Data from Neighboring Region

Contact Info

Product

Resources

About