Damage identification and assessment using image processing on post-disaster satellite imagery

Joshi, Aparna R.; Tarte, Isha; Suresh, Sreeja; Koolagudi, Shashidhar G.

doi:10.1109/ghtc.2017.8239286

Cited by 16 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model learned these differences between pre-and post-disaster images as the image features for detecting the change. In previous studies, such as those presented by Joshi et al [31], only pre-disaster imagery was used for flood detection.…”

Section: Methodsmentioning

confidence: 99%

UAVs in Disaster Management: Application of Integrated Aerial Imagery and Convolutional Neural Network for Flood Detection

et al. 2021

View full text Add to dashboard Cite

Floods have been a major cause of destruction, instigating fatalities and massive damage to the infrastructure and overall economy of the affected country. Flood-related devastation results in the loss of homes, buildings, and critical infrastructure, leaving no means of communication or travel for the people stuck in such disasters. Thus, it is essential to develop systems that can detect floods in a region to provide timely aid and relief to stranded people, save their livelihoods, homes, and buildings, and protect key city infrastructure. Flood prediction and warning systems have been implemented in developed countries, but the manufacturing cost of such systems is too high for developing countries. Remote sensing, satellite imagery, global positioning system, and geographical information systems are currently used for flood detection to assess the flood-related damages. These techniques use neural networks, machine learning, or deep learning methods. However, unmanned aerial vehicles (UAVs) coupled with convolution neural networks have not been explored in these contexts to instigate a swift disaster management response to minimize damage to infrastructure. Accordingly, this paper uses UAV-based aerial imagery as a flood detection method based on Convolutional Neural Network (CNN) to extract flood-related features from the images of the disaster zone. This method is effective in assessing the damage to local infrastructures in the disaster zones. The study area is based on a flood-prone region of the Indus River in Pakistan, where both pre-and post-disaster images are collected through UAVs. For the training phase, 2150 image patches are created by resizing and cropping the source images. These patches in the training dataset train the CNN model to detect and extract the regions where a flood-related change has occurred. The model is tested against both pre-and post-disaster images to validate it, which has positive flood detection results with an accuracy of 91%. Disaster management organizations can use this model to assess the damages to critical city infrastructure and other assets worldwide to instigate proper disaster responses and minimize the damages. This can help with the smart governance of the cities where all emergent disasters are addressed promptly.

show abstract

Section: Methodsmentioning

confidence: 99%

UAVs in Disaster Management: Application of Integrated Aerial Imagery and Convolutional Neural Network for Flood Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Bagging is the term used to describe the convergence of decision trees. The researchers of [29] utilized a random forest to identify post-disaster alterations. Likewise, the researchers of [30] were employed to identify building issues.…”

Section: State-of-the-artmentioning

confidence: 99%

Machine Learning Based Real Time-Heuristic Sensor Data Analytics For Early Warning Prediction

Pal¹,

Mishra²,

Haldorai³

et al. 2021

Preprint

View full text Add to dashboard Cite

Landslides have the potential to cause significant property damage as well as fatalities. Landslides are identified by real-time heuristic data analysis acquired using wireless sensor networks (WSNs) in changing environments. People can abandon dangerous locations earlier when landslides are forecasted. In this paper, the early warning prediction system developed using machine learning; Artificial Neural Networks (ANNs) provide precise predictions. The weight coefficients of ANN can be adjusted exactly enough by network functional training. In the case of unbalanced data distribution, the proposed ANN model is unable to learn the sample data pattern. This results in incorrect prediction and therefore, a switching method is utilized to switch between alternative predictors based on the current environmental state. Furthermore, the proposed model has been developed to forecast and compensate for errors during the prediction phase. Thus, the proposed model can enhance precise prediction, and an early warning prediction system of landslides can issue warnings 44.2 minutes before a landslide occurrence.

show abstract

“…The spatial distributions of the RF and the SVM-based assessment maps showed a similar correlation coefficient, was indicated that the classification capacity of the two methods is similar in the majority of cases. Joshi et al introduced a methodology for detection of damage post disasters by examining the textural features from high resolution aerial imagery [59]. The proposed technique considered DT, NB, SVM, RF, Voting Classifier and Adaptive Booster, and were compared to identify damaged regions from aerial images using only pre-event images as the input.…”

Section: Emergency Evaluationmentioning

confidence: 99%

Analytics and Evolving Landscape of Machine Learning for Emergency Response

Hong

Akerkar

2019

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

The advances in information technology have had a profound impact on emergency management by making unprecedented volumes of data available to the decision makers. This has resulted in new challenges related to the effective management of large volumes of data. In this regard, the role of machine learning in mass emergency and humanitarian crises is constantly evolving and gaining traction. As a branch of artificial intelligence, machine learning technologies have the huge advantages of self-learning, self-organization, and self-adaptation, along with simpleness, generality and robustness. Although these technologies do not perfectly solve issues in emergency management. They have greatly improved the capability and effectiveness of emergency management. In this paper, we review the use of machine learning techniques to support the decision-making processes for the emergency management and discuss their challenges. Additionally, we discuss the challenges and opportunities of the machine learning approaches and intelligent data analysis to distinct phases of emergency management. Based on the literature review, we observe a trend to move from narrow in scope, problem-specific applications of machine learning to solutions that address a wider spectrum of problems, such as situational awareness and real-time threat assessment using diverse streams of data. This chapter also focuses on crowd-sourcing approaches with machine learning to achieve better understanding and decision support during an emergency. Keywords emergency management • crisis analytics • data analysis • data mining • machine learning • decision making • situational awareness • real-time assessment • deep learning • data streams

show abstract

Damage identification and assessment using image processing on post-disaster satellite imagery

Cited by 16 publications

References 19 publications

UAVs in Disaster Management: Application of Integrated Aerial Imagery and Convolutional Neural Network for Flood Detection

UAVs in Disaster Management: Application of Integrated Aerial Imagery and Convolutional Neural Network for Flood Detection

Machine Learning Based Real Time-Heuristic Sensor Data Analytics For Early Warning Prediction

Analytics and Evolving Landscape of Machine Learning for Emergency Response

Contact Info

Product

Resources

About