Postevent Reconnaissance Image Documentation Using Automated Classification

Abstract

Reconnaissance teams are charged with collecting perishable data after a natural disaster. In the field, these engineers typically record their observations through images. Each team takes many views of both exterior and interior buildings and frequently collects associated metadata that reflect information represented in images, such as global positioning system (GPS) devices, structural drawings, timestamp, and measurements. Large quantities of images with a wide variety of contents are collected. The window of opportunity is short, and engineers need to provide accurate and rich descriptions of such images before the details are forgotten. In this paper, an automated approach is developed to organize and document such scientific information in an efficient and rapid manner. Deep convolutional neural network algorithms were successfully implemented to extract robust features of key visual contents in the images. A schema is designed based on the realistic needs of field teams examining buildings. A significant number of images collected from past earthquakes were used to train robust classifiers to automatically classify the images. The classifiers and associated schema were used to automatically generate individual reports for buildings.

Postdisaster image‐based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks

“…CNNs have been successfully applied in civil engineering applications for image classifications. These include metal surface defects detection (Soukup & Huber-Mörk, 2014), post-disaster collapse classification (Yeum, Dyke, Ramirez, & Benes, 2016), joint damage detection through a onedimensional CNN (Abdeljaber, Avci, Kiranyaz, Gabbouj, & Inman, 2017), concrete crack detection using a sliding window technique (Cha, Choi, & Büyüköztürk, 2017), pavement crack detection (Zhang et al, 2017;Vetrivel, Gerke, Kerle, Nex, & Vosselman, 2018), structural damage detection with feature extracted from low-level sensor data (Lin, Nie, & Ma, 2017), structural damage classification with the proposal of Structural ImageNet (Gao & Mosalam, 2018). Apart from the CNN-based classification, other powerful classification algorithms such as Enhanced Probabilistic Neural Network with Local Decision Circles (EPNN) and the new Neural Dynamic Classification (NDC) were successfully developed in recent years (Ahmadlou & Adeli, 2010;Rafiei & Adeli, 2017).…”

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

“…Automating some of the procedures associated with building damage surveys will enable reconnaissance teams to more rapidly gather and analyze these large volumes of perishable information. Recent demonstrations of automation include scene recognition and object detection with large volumes of images collected after an event by exploiting new developments in convolutional neural networks (CNNs) [2,11,32,33]. These techniques, which fall into the broad category of artificial intelligence, are gaining traction.…”

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

“…The simplest way to resolve scale is to capture images by a reference object of known dimension (e.g., pen, ruler, paper; Yeum, Dyke et al., 2019). Hence, if the inspection area and reference object are present on the same plane, scale may be resolved using a simple pixel to length relationship.…”