A Comparative Study of Texture and Convolutional Neural Network Features for Detecting Collapsed Buildings After Earthquakes Using Pre- and Post-Event Satellite Imagery

Min Ji,Lanfa Liu,Manfred F Buchroithner,Runlin Du

doi:10.3390/rs11101202

Min Ji, Lanfa Liu + Show 2 more

Open Access

https://doi.org/10.3390/rs11101202

Copy DOI

Journal: Remote sensing	Publication Date: May 21, 2019
Citations: 64	License type: CC BY 4.0

Affiliation: TU Dresden, Qingdao Institute of Marine Geology

Abstract

The accurate and quick derivation of the distribution of damaged building must be considered essential for the emergency response. With the success of deep learning, there is an increasing interest to apply it for earthquake-induced building damage mapping, and its performance has not been compared with conventional methods in detecting building damage after the earthquake. In the present study, the performance of grey-level co-occurrence matrix texture and convolutional neural network (CNN) features were comparatively evaluated with the random forest classifier. Pre- and post-event very high-resolution (VHR) remote sensing imagery were considered to identify collapsed buildings after the 2010 Haiti earthquake. Overall accuracy (OA), allocation disagreement (AD), quantity disagreement (QD), Kappa, user accuracy (UA), and producer accuracy (PA) were used as the evaluation metrics. The results showed that the CNN feature with random forest method had the best performance, achieving an OA of 87.6% and a total disagreement of 12.4%. CNNs have the potential to extract deep features for identifying collapsed buildings compared to the texture feature with random forest method by increasing Kappa from 61.7% to 69.5% and reducing the total disagreement from 16.6% to 14.1%. The accuracy for identifying buildings was improved by combining CNN features with random forest compared with the CNN approach. OA increased from 85.9% to 87.6%, and the total disagreement reduced from 14.1% to 12.4%. The results indicate that the learnt CNN features can outperform texture features for identifying collapsed buildings using VHR remotely sensed space imagery.

Highlights

Remote sensing imagery has been widely adopted to assess damaged buildings induced by an earthquake
We compared the performance of texture and convolutional neural network (CNN) features with the random forest classifier to distinguish collapsed and noncollapsed buildings after the 2010 Haiti earthquake using pre- and post-event satellite imagery
Deep learning has proven its value for many problems, and is sometimes even able to surpass human ability to solve highly computational tasks, such as ImageNet Large Scale Visual Recognition Competition (ILSVRC) image classification and the highly mediatized Go match [59,60]

Summary

Introduction

A novel method was proposed to detect damaged buildings using high-resolution remote sensing images and three-dimensional GIS data by Tu et al in Reference [10]. OBIA has been applied to detect earthquake damage using remote sensing imagery since 1988 [13]. ECognition software was considered for image segmentation and classification to detect damaged buildings after the 2010 Haiti earthquake [20]. OBIA has shown the potential for earthquake damage detection, while the application of convolutional neural networks (CNNs) is still limited and worth to be explored to discover its advantages. It comprises three convolutional and activation layers, two max-pooling layers, a global average pooling layer, and a traditional fully connected layer.

GLCM Texture Features

Random Forest

Evaluation Metrics

Performance of CNN-RF

Performance of Texture-RF

Conclusions