Real-time Quantitative Visual Inspection using Extended Reality
-
Published:2021-01-15
Issue:1
Volume:6
Page:1-3
-
ISSN:2562-0444
-
Container-title:Journal of Computational Vision and Imaging Systems
-
language:
-
Short-container-title:J. Comp. Vis. Imag. Sys.
Author:
Al-Sabbag Zaid Abbas,Connelly Jason Paul,Yeum Chul Min,Narasimhan Sriram
Abstract
In this study, we propose a technique for quantitative visual inspection that can quantify structural damage using extended reality (XR). The XR headset can display and overlay graphical information on the physical space and process the data from the built-in camera and depth sensor. Also, the device permits accessing and analyzing image and video stream in real-time and utilizing 3D meshes of the environment and camera pose information. By leveraging these features for the XR headset, we build a workflow and graphic interface to capture the images, segment damage regions, and evaluate the physical size of damage. A deep learning-based interactive segmentation algorithm called f-BRS was deployed to precisely segment damage regions through the XR headset. A ray-casting algorithm is implemented to obtain 3D locations corresponding to the pixel locations of the damage region on the image. The size of the damage region is computed from the 3D locations of its boundary. The performance of the proposed method is demonstrated through a field experiment at an in-service bridge where spalling damage is present at its abutment. The experiment shows that the proposed method provides sub-centimeter accuracy for the size estimation.
Publisher
University of Waterloo
Subject
Industrial and Manufacturing Engineering
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献