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

TL;DR

This paper introduces a high-resolution vision transformer-based semantic segmentation network that efficiently processes detailed inspection images, preserving fine damage features and global context for civil structure assessment.

Contribution

The study proposes a novel vision transformer architecture with Laplacian pyramids that effectively handles high-resolution images without losing detail or increasing computational load.

Findings

Achieved accurate pixel-wise damage detection on bridge inspection images.

Outperformed traditional downsampling methods in preserving fine details.

Demonstrated computational efficiency in processing high-resolution visual data.

Abstract

Visual inspection is predominantly used to evaluate the state of civil structures, but recent developments in unmanned aerial vehicles (UAVs) and artificial intelligence have increased the speed, safety, and reliability of the inspection process. In this study, we develop a semantic segmentation network based on vision transformers and Laplacian pyramids scaling networks for efficiently parsing high-resolution visual inspection images. The massive amounts of collected high-resolution images during inspections can slow down the investigation efforts. And while there have been extensive studies dedicated to the use of deep learning models for damage segmentation, processing high-resolution visual data can pose major computational difficulties. Traditionally, images are either uniformly downsampled or partitioned to cope with computational demands. However, the input is at risk of losing local fine details, such as thin cracks, or global contextual information. Inspired by super-resolution architectures, our vision transformer model learns to resize high-resolution images and masks to retain both the valuable local features and the global semantics without sacrificing computational efficiency. The proposed framework has been evaluated through comprehensive experiments on a dataset of bridge inspection report images using multiple metrics for pixel-wise materials detection.