Probabilistic Urban Structural Damage Classification Using Bitemporal Satellite Images

2010 ◽  
Vol 26 (1) ◽  
pp. 87-109 ◽  
Author(s):  
ZhiQiang Chen ◽  
Tara C. Hutchinson
Keyword(s):  
Structural Damage ◽  
Satellite Images ◽  
Probabilistic Approach ◽  
Damage Classification ◽  
Classification Framework ◽  
Sensing Technology ◽  
Probabilistic Classification ◽  
Multiclass Classifier ◽  
Post Disaster

Recent research endeavors in civil engineering have attempted to apply remote sensing technology to urban damage assessment as an aid for post-disaster reconnaissance and recovery. In these attempts, urban structural damage is identified based on pre- and post-disaster satellite images with the use of a pattern classification approach. The result is usually presented in a damage map wherein categorical damage levels, such as “fully collapsed,” “partially collapsed,” or “intact,” are assigned to urban subregions or individual structures in images. However, a major limitation in past attempts is the use of deterministic approaches to classify damage levels. In general, these approaches are not able to capture the inherent uncertainties of structural damage and lack scalability when analyzing damage to built urban subregions of different sizes. To address this, a probabilistic classification framework by means of a multiclass classifier is proposed. By applying this probabilistic approach, classification of urban damage provides posterior probabilities, which can be used to quantify decision uncertainties and to obtain regional urban damage classification. Numerical experiments are conducted using satellite images acquired from a recent earthquake and a tsunami event, namely the 2003 Bam, Iran Earthquake, and the 2004 India Ocean Tsunami.

scholarly journals Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data

2019 ◽  
Vol 11 (20) ◽  
pp. 2427 ◽  
Author(s):  
Saman Ghaffarian ◽  
Norman Kerle ◽  
Edoardo Pasolli ◽  
Jamal Jokar Arsanjani
Keyword(s):  
Deep Learning ◽  
Structural Damage ◽  
Satellite Images ◽  
Conditional Random Field ◽  
The Philippines ◽  
Learning Framework ◽  
Training Samples ◽  
The Status ◽  
Multi Temporal ◽  
Post Disaster

First responders and recovery planners need accurate and quickly derived information about the status of buildings as well as newly built ones to both help victims and to make decisions for reconstruction processes after a disaster. Deep learning and, in particular, convolutional neural network (CNN)-based approaches have recently become state-of-the-art methods to extract information from remote sensing images, in particular for image-based structural damage assessment. However, they are predominantly based on manually extracted training samples. In the present study, we use pre-disaster OpenStreetMap building data to automatically generate training samples to train the proposed deep learning approach after the co-registration of the map and the satellite images. The proposed deep learning framework is based on the U-net design with residual connections, which has been shown to be an effective method to increase the efficiency of CNN-based models. The ResUnet is followed by a Conditional Random Field (CRF) implementation to further refine the results. Experimental analysis was carried out on selected very high resolution (VHR) satellite images representing various scenarios after the 2013 Super Typhoon Haiyan in both the damage and the recovery phases in Tacloban, the Philippines. The results show the robustness of the proposed ResUnet-CRF framework in updating the building map after a disaster for both damage and recovery situations by producing an overall F1-score of 84.2%.

Classification of vegetation in Cucphuong National Park with the aim of large-scale mapping, Vietnam

1996 ◽  
pp. 64-67 ◽  
Author(s):  
Nguen Nghia Thin ◽  
Nguen Ba Thu ◽  
Tran Van Thuy
Keyword(s):  
National Park ◽  
Large Scale ◽  
Satellite Images ◽  
Field Work ◽  
Aerial Photographs ◽  
Vegetation Map ◽  
Dense Forest ◽  
Broad Leaved Forest ◽  
Leaved Forest

The tropical seasonal rainy evergreen broad-leaved forest vegetation of the Cucphoung National Park has been classified and the distribution of plant communities has been shown on the map using the relations of vegetation to geology, geomorphology and pedology. The method of vegetation mapping includes: 1) the identifying of vegetation types in the remote-sensed materials (aerial photographs and satellite images); 2) field work to compile the interpretation keys and to characterize all the communities of a study area; 3) compilation of the final vegetation map using the combined information. In the classification presented a number of different level vegetation units have been identified: formation classes (3), formation sub-classes (3), formation groups (3), formations (4), subformations (10) and communities (19). Communities have been taken as mapping units. So in the vegetation map of the National Park 19 vegetation categories has been shown altogether, among them 13 are natural primary communities, and 6 are the secondary, anthropogenic ones. The secondary succession goes through 3 main stages: grassland herbaceous xerophytic vegetation, xerophytic scrub, dense forest.

scholarly journals Uncertainty-Aware Deep Learning-Based Cardiac Arrhythmias Classification Model of Electrocardiogram Signals

Computers ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 82
Author(s):  
Ahmad O. Aseeri
Keyword(s):  
Deep Learning ◽  
Cardiac Arrhythmias ◽  
Large Scale ◽  
Clinical Decision Making ◽  
Probabilistic Approach ◽  
Classification Model ◽  
Gating Mechanism ◽  
Uncertainty Estimates ◽  
Wide Range

Deep Learning-based methods have emerged to be one of the most effective and practical solutions in a wide range of medical problems, including the diagnosis of cardiac arrhythmias. A critical step to a precocious diagnosis in many heart dysfunctions diseases starts with the accurate detection and classification of cardiac arrhythmias, which can be achieved via electrocardiograms (ECGs). Motivated by the desire to enhance conventional clinical methods in diagnosing cardiac arrhythmias, we introduce an uncertainty-aware deep learning-based predictive model design for accurate large-scale classification of cardiac arrhythmias successfully trained and evaluated using three benchmark medical datasets. In addition, considering that the quantification of uncertainty estimates is vital for clinical decision-making, our method incorporates a probabilistic approach to capture the model’s uncertainty using a Bayesian-based approximation method without introducing additional parameters or significant changes to the network’s architecture. Although many arrhythmias classification solutions with various ECG feature engineering techniques have been reported in the literature, the introduced AI-based probabilistic-enabled method in this paper outperforms the results of existing methods in outstanding multiclass classification results that manifest F1 scores of 98.62% and 96.73% with (MIT-BIH) dataset of 20 annotations, and 99.23% and 96.94% with (INCART) dataset of eight annotations, and 97.25% and 96.73% with (BIDMC) dataset of six annotations, for the deep ensemble and probabilistic mode, respectively. We demonstrate our method’s high-performing and statistical reliability results in numerical experiments on the language modeling using the gating mechanism of Recurrent Neural Networks.

scholarly journals Improving Land Cover Classification Using Genetic Programming for Feature Construction

2021 ◽  
Vol 13 (9) ◽  
pp. 1623
Author(s):  
João E. Batista ◽  
Ana I. R. Cabral ◽  
Maria J. P. Vasconcelos ◽  
Leonardo Vanneschi ◽  
Sara Silva
Keyword(s):  
Land Cover ◽  
Genetic Programming ◽  
Satellite Images ◽  
State Of The Art ◽  
Binary Classification ◽  
Feature Construction ◽  
Classification Problems ◽  
Construction Methods ◽  
Box Models

Genetic programming (GP) is a powerful machine learning (ML) algorithm that can produce readable white-box models. Although successfully used for solving an array of problems in different scientific areas, GP is still not well known in the field of remote sensing. The M3GP algorithm, a variant of the standard GP algorithm, performs feature construction by evolving hyperfeatures from the original ones. In this work, we use the M3GP algorithm on several sets of satellite images over different countries to create hyperfeatures from satellite bands to improve the classification of land cover types. We add the evolved hyperfeatures to the reference datasets and observe a significant improvement of the performance of three state-of-the-art ML algorithms (decision trees, random forests, and XGBoost) on multiclass classifications and no significant effect on the binary classifications. We show that adding the M3GP hyperfeatures to the reference datasets brings better results than adding the well-known spectral indices NDVI, NDWI, and NBR. We also compare the performance of the M3GP hyperfeatures in the binary classification problems with those created by other feature construction methods such as FFX and EFS.

scholarly journals Structural Damage Classification in a Jacket-Type Wind-Turbine Foundation Using Principal Component Analysis and Extreme Gradient Boosting

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2748
Author(s):  
Jersson X. Leon-Medina ◽  
Maribel Anaya ◽  
Núria Parés ◽  
Diego A. Tibaduiza ◽  
Francesc Pozo
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Wind Turbine ◽  
Structural Damage ◽  
Principal Component ◽  
Gradient Boosting ◽  
Damage Classification ◽  
Linear Feature ◽  
Linear Feature Extraction ◽  
Extreme Gradient Boosting

Damage classification is an important topic in the development of structural health monitoring systems. When applied to wind-turbine foundations, it provides information about the state of the structure, helps in maintenance, and prevents catastrophic failures. A data-driven pattern-recognition methodology for structural damage classification was developed in this study. The proposed methodology involves several stages: (1) data acquisition, (2) data arrangement, (3) data normalization through the mean-centered unitary group-scaling method, (4) linear feature extraction, (5) classification using the extreme gradient boosting machine learning classifier, and (6) validation applying a 5-fold cross-validation technique. The linear feature extraction capabilities of principal component analysis are employed; the original data of 58,008 features is reduced to only 21 features. The methodology is validated with an experimental test performed in a small-scale wind-turbine foundation structure that simulates the perturbation effects caused by wind and marine waves by applying an unknown white noise signal excitation to the structure. A vibration-response methodology is selected for collecting accelerometer data from both the healthy structure and the structure subjected to four different damage scenarios. The datasets are satisfactorily classified, with performance measures over 99.9% after using the proposed damage classification methodology.

Sign in / Sign up

Export Citation Format

Share Document