An image-based seismic damage assessment system

Abstract

Surveillance systems are commonly used by command centers to monitor and assess seismic damage inside buildings, such as schools, shopping malls, office buildings and skyscrapers. It is expected that checking camera images manually on monitors can be a very time-consuming and inefficient process, especially for a large surveillance system. One of the alternative ways is to first deploy sensors to monitor objects inside buildings, such as tables, cabinets, bookcases and so on, and, after fusing sensor data, to assess damage. However, deploying sensors can be impractical and costly when there are too many objects needed to be monitored. In this paper, we present IDEAS, an image-based disaster damage assessment system, to evaluate seismic damage inside buildings. IDEAS first compares images taken inside a building before and after an earthquake, it then maps the damage to a Mercalli intensity scale. In order to investigate the effectiveness and accuracy of IDEAS, we collect over forty pairs of closed-circuit television (CCTV) images from Youtube website. Each pair of images represents a real scenario of an earthquake inside a building. Our results show that IDEAS performs better than existing methods and can achieve an average accuracy of 97.6 % in mapping Mercalli intensity scale.

Earthquakes Reconnaissance Data Sources, a Literature Review

“…To determine the accuracy of IDEAS, 40 pairs of CCTV images from Youtube website were collected. The test reports an accuracy of 97.6% in mapping the Mercalli intensity scale [57].…”

“…[26] SAR [12], [40] InSAR [41], [42], [43], [ [53], [54], [55] Closed-circuit television videos (CCTV) [56], [57] Missions deployed, or missions that have had their results published during the period covered by this literature review are Albania [47,58], Puerto Rico [45,46], Mayotte [52], Mexico [28][29][30], Palu -North Sulawesi (Indonesia) [53,56,59], Hualien (China) [51], Central Italy [32,33,35,60], Muisne (Ecuador) [35], Nepal [1,40,49], and Napa -California (USA) [54,55], Haiti [12] and L'Aquila (Italy) [14,37]. The location of major earthquakes epicentres from 2014 -2019 included as case studies in this literature review is depicted in Figure 3.…”

“…This system first compares images taken inside a building before and after an earthquake. Later these images are used to map the damage according to a Mercalli intensity scale [57]. To perform the earthquake intensity scale assessment, IDEAS adopts scale-invariant feature transformation (SIFT) to extract the information of non-structural objects moved.…”

“…To perform the earthquake intensity scale assessment, IDEAS adopts scale-invariant feature transformation (SIFT) to extract the information of non-structural objects moved. Afterwards, IDEA uses the information and the size variants of non-structural objects moved for damage assessment of the buildings [57]. To determine the accuracy of IDEAS, 40 pairs of CCTV images from Youtube website were collected.…”

Earthquakes Reconnaissance Data Sources, a Literature Review

“…[25] SAR [10], [39] InSAR [40], [41], [42], [43 [52], [53], [54] Closed-circuit television videos (CCTV) [55], [56] Missions deployed, or missions that have had their results published during the period covered by this literature review are Albania [46,57], Puerto Rico [44,45], Mayotte [51], Mexico [27][28][29], Palu -North Sulawesi (Indonesia) [52,55,58], Hualien (China) [50],…”