4.7 Article

Disaster Intensity-Based Selection of Training Samples for Remote Sensing Building Damage Classification

期刊

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3046004

关键词

Automatic labeling; building damage; multiregularization parameters; support vector machine (SVM)

资金

  1. National Fund for Scientific, Technological, and Technological Innovation Development (Fondecyt-Peru) within the framework of the Project for the Improvement and Extension of the Services of the National System of Science, Technology and Technological Inn [038-2019]
  2. Japan Science and Technology Agency (JST) CREST [JP-MJCR1411]
  3. Japan Society for the Promotion of Science (JSPS) Kakenhi [17H06108]
  4. Helmholtz Association [PD-305]
  5. Core Research Cluster of Disaster Science at Tohoku University (a Designated National University)

向作者/读者索取更多资源

This article discusses the application of machine learning in identifying damaged buildings after large-scale disasters, with a focus on disaster intensity that can be modeled numerically or instrumentally. Two automatic procedures for detecting severely damaged buildings are introduced to avoid the time cost of collecting labeled building samples through field surveys or visual inspection of optical images.
Previous applications of machine learning in remote sensing for the identification of damaged buildings in the aftermath of a large-scale disaster have been successful. However, standard methods do not consider the complexity and costs of compiling a training data set after a large-scale disaster. In this article, we study disaster events in which the intensity can be modeled via numerical simulation and/or instrumentation. For such cases, two fully automatic procedures for the detection of severely damaged buildings are introduced. The fundamental assumption is that samples that are located in areas with low disaster intensity mainly represent nondamaged buildings. Furthermore, areas with moderate to strong disaster intensities likely contain damaged and nondamaged buildings. Under this assumption, a procedure that is based on the automatic selection of training samples for learning and calibrating the standard support vector machine classifier is utilized. The second procedure is based on the use of two regularization parameters to define the support vectors. These frameworks avoid the collection of labeled building samples via field surveys and/or visual inspection of optical images, which requires a significant amount of time. The performance of the proposed method is evaluated via application to three real cases: the 2011 Tohoku-Oki earthquake-tsunami, the 2016 Kumamoto earthquake, and the 2018 Okayama floods. The resulted accuracy ranges between 0.85 and 0.89, and thus, it shows that the result can be used for the rapid allocation of affected buildings.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据