Chu, Honghu;
Yu, Diran;
Chen, Weiwei;
Ma, Jun;
Deng, Lu;
(2024)
A rendering-based lightweight network for segmentation of high-resolution crack images.
Computer-Aided Civil and Infrastructure Engineering
10.1111/mice.13290.
(In press).
Preview |
PDF
A Rendering-based Lightweight Network for Segmentation of High-resolution Crack Images-accepted version- CACAIE paper.pdf - Accepted Version Download (2MB) | Preview |
Abstract
High-resolution (HR) crack images provide detailed structural assessments crucial for maintenance planning. However, the discrete nature of feature extraction in mainstream deep learning algorithms and computational limitations hinder refined segmentation. This study introduces a rendering-based lightweight crack segmentation network (RLCSN) designed to efficiently predict refined masks for HR crack images. The RLCSN combines a deep semantic feature extraction architecture—merging Transformer with a super-resolution boundary-guided branch—to reduce environmental noise and preserve crack edge details. It also incorporates customized point-wise refined rendering for training and inference, focusing computational resources on critical areas, and an efficient sparse training method to ensure efficient inference on commercial mobile computing platforms. Each RLCSN's components are validated through ablation studies and field tests, demonstrating its capability to enable unmanned aerial vehicle-based inspections to detect cracks as narrow as 0.15 mm from a distance of 3 m, thereby enhancing inspection safety and efficiency.
| Type: | Article |
|---|---|
| Title: | A rendering-based lightweight network for segmentation of high-resolution crack images |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1111/mice.13290 |
| Publisher version: | http://dx.doi.org/10.1111/mice.13290 |
| Language: | English |
| Additional information: | © 2024 The Author(s). Computer-Aided Civil and Infrastructure Engineering published by Wiley Periodicals LLC on behalf of Editor. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10195021 |
Archive Staff Only
 |
View Item |
