Automated building image extraction from 360° panoramas for postdisaster evaluation

Abstract

After a disaster, teams of structural engineers collect vast amounts of images from damaged buildings to obtain new knowledge and extract lessons from the event. However, in many cases, the images collected are captured without sufficient spatial context. When damage is severe, it may be quite difficult to even recognize the building. Accessing images of the predisaster condition of those buildings is required to accurately identify the cause of the failure or the actual loss in the building. Here, to address this issue, we develop a method to automatically extract pre‐event building images from 360° panorama images (panoramas). By providing a geotagged image collected near the target building as the input, panoramas close to the input image location are automatically downloaded through street view services (e.g., Google or Bing in the United States). By computing the geometric relationship between the panoramas and the target building, the most suitable projection direction for each panorama is identified to generate high‐quality 2D images of the building. Region‐based convolutional neural networks are exploited to recognize the building within those 2D images. Several panoramas are used so that the detected building images provide various viewpoints of the building. To demonstrate the capability of the technique, we consider residential buildings in Holiday Beach in Rockport, Texas, United States, that experienced significant devastation in Hurricane Harvey in 2017. Using geotagged images gathered during actual postdisaster building reconnaissance missions, we verify the method by successfully extracting residential building images from Google Street View images, which were captured before the event.

Towards fully automated post-event data collection and analysis: Pre-event and post-event information fusion

“…In the pre-event stream, multiple external views of each building, collected before the event, are required. We employ an automated method we previously developed to extract suitable pre-event residential building images from typical street view panoramas [17,34]. We design three independent classifiers, shown in, Fig.…”

“…These images may be critical for damage surveys, as after an event a building may be so severely damaged that its original attributes may not be decipherable. An automated technique has been developed to extract high-quality pre-event images from several viewpoints using only a single geo-tagged image or its GPS data [17]. Additionally, after the event, images may be similarly collected with spherical cameras to quickly record the external appearance of buildings and support visual assessment [17,34].…”

“…An automated technique has been developed to extract high-quality pre-event images from several viewpoints using only a single geo-tagged image or its GPS data [17]. Additionally, after the event, images may be similarly collected with spherical cameras to quickly record the external appearance of buildings and support visual assessment [17,34]. The integration of these readily available data, efficient and automated analytics capabilities, and processing power, can greatly improve the efficiency of the reconnaissance missions.…”

Learning‐based image scale estimation using surface textures for quantitative visual inspection of regions‐of‐interest

“…Since access is arguably the main challenge associated with collecting visual data for large‐scale civil infrastructure, remote and automated data collection systems have been proposed to increase the efficiency of inspections. Vision sensors (e.g., RGB, infrared cameras) integrated with mobile and static sensing platforms (e.g., drones, surveillance cameras, crawling robots) are used to access and capture inspection regions with necessary levels of detail (Charron et al., 2019; J. Choi, Yeum, Dyke, & Jahanshahi, 2018; Hoskere, Park, Yoon, & Spencer, 2019; Jiang & Zhang, 2020; Lenjani, Yeum, Dyke, & Bilionis, 2020; Narazaki et al., 2020; Rafiei & Adeli, 2017; Rafiei, Khushefati, Demirboga, & Adeli, 2017). Subsequently, methods to extract those regions of interest (ROIs) from visual data have been developed to conduct specific visual inspection tasks outlined in the manual (e.g., damage detection and classification, structural components, geometric changes; An, Jang, Kim, & Cho, 2018; Bao, Tang, Li, & Zhang, 2018; W. Choi & Cha, 2019; Gao & Mosalam, 2018; Hoskere, Narazaki, Hoang, & Spencer, 2018; Kong & Li, 2019; Lee, Lee, Jeong, Lee, & Sim, 2020; Xu, Wei, Bao, & Li, 2019; Yeum, Choi, & Dyke, 2019).…”

Automated Indoor Image Localization to Support a Post-Event Building Assessment

“…With the frequency of recent events and the ease with which an increasing number of images can be collected (e.g., smartphone [1,2], streetview [3,4], and aerial images [5]), the number of images The remainder of this paper is organized as follows. Section 2 starts with a review of the state-of-the-art in path reconstruction techniques.…”