English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Visual inspection is predominantly used to evaluate the state of civilstructures, but recent developments in unmanned aerial vehicles (UAVs) andartificial intelligence have increased the speed, safety, and reliability ofthe inspection process. In this study, we develop a semantic segmentationnetwork based on vision transformers and Laplacian pyramids scaling networksfor efficiently parsing high-resolution visual inspection images. The massiveamounts of collected high-resolution images during inspections can slow downthe investigation efforts. And while there have been extensive studiesdedicated to the use of deep learning models for damage segmentation,processing high-resolution visual data can pose major computationaldifficulties. Traditionally, images are either uniformly downsampled orpartitioned to cope with computational demands. However, the input is at riskof losing local fine details, such as thin cracks, or global contextualinformation. Inspired by super-resolution architectures, our vision transformermodel learns to resize high-resolution images and masks to retain both thevaluable local features and the global semantics without sacrificingcomputational efficiency. The proposed framework has been evaluated throughcomprehensive experiments on a dataset of bridge inspection report images usingmultiple metrics for pixel-wise materials detection.

High-Resolution Vision Transformers for Pixel-Level Identification of Structural Components and Damage