Bridge related damage quantification using unmanned aerial vehicle imagery

Abstract

Visual inspection procedures remain the primary method of infrastructure assessment throughout the USA, but their shortcomings are numerous. In addition to their widely acknowledged variability and subjectivity, the large scale of civil infrastructure systems presents expensive access and time requirements that constrain the frequency of visual inspections and result in poor temporal resolution, which hampers effective decision-making. To overcome this challenge, the research reported herein aimed to assess the ability of computer algorithms together with imagery collected by unmanned aerial vehicles (UAV) to extract accurate and quantitative information to help inform infrastructure management decisions. Techniques such as homography and lens distortion correction are used in this article in a post-processing framework that allows the use of color images obtained by UAVs for actual damage quantification measurements. The experiments described in this article utilize a UAV with a mounted camera and provide measurements from a representative infrastructure mockup with several simulated damage scenarios. Deformation measurements, change detection (related to structural features and the size of deterioration), and crack pattern identification were all analyzed. The results indicated that the developed post-processing algorithms were able to extract quantitative information from UAV captured imagery.

Benchmarking Image Processing Algorithms for Unmanned Aerial System-Assisted Crack Detection in Concrete Structures

“…Autonomous inspection could be a cost-effective solution to these problems if the accuracy of human inspection can be matched [3][4][5][6][7][8][9]. Image-based inspection of infrastructure for concrete delamination [10][11][12][13], cracks [14][15][16][17], and spalls [18,19] using unmanned aerial systems (UASs) have been proven effective based on previous literature [20].…”

Convolutional neural networks for automated damage recognition and damage type identification

“…Many of the presented methodologies act upon a particular type of image, like thermal imagery or three‐dimensional scene reconstruction in order to simplify the detection task. Other approaches require significant filtering, feature extraction, and transformations to address varying field conditions like lighting or varying scale …”

Multiscale deformation measurements using multispectral optical metrology

“…Efforts have also been reported on assisting expert users with devices capable of accurately extracting spatial coordinates from light emitters for structural analyses with the use of artificial intelligence . More recently, the authors of this article extended the use of optical metrology to unmanned aerial systems and remotely measured beam deflections …”

“…[15] More recently, the authors of this article extended the use of optical metrology to unmanned aerial systems and remotely measured beam deflections. [16,17] In parallel, the digital image correlation (DIC) method has been used extensively in applications ranging from the micro-to the structural scale. [18][19][20][21][22][23][24] In fact, DIC has been used in experimental testing to measure deformation.…”