Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Smart Structures and Systems Volume 31, Number 4, April 2023 , pages 351-363 DOI: https://doi.org/10.12989/sss.2023.31.4.351 |
|
|
|
Twin models for high-resolution visual inspections |
||
Seyedomid Sajedi, Kareem A. Eltouny and Xiao Liang
|
||
| Abstract | ||
| Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate highresolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physicsbased graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2nd International Competition for Structural Health Monitoring. | ||
| Key Words | ||
| computer vision; crack detection; damage detection; deep learning; IC-SHM; semantic segmentation; visual inspections | ||
| Address | ||
| Department of Civil, Structural and Environmental Engineering, University at Buffalo, the State University of New York, Buffalo, New York, 14260, USA. | ||