CrackFormer: A reinforcement learning-enhanced Swin Transformer V3 framework for high-fidelity detection and segmentation of pavement surface cracks
Authors:
- Rizwan UllahRURizwan Ullah
- Fazale WahabFWFazale Wahab
- Hazrat BilalHBHazrat Bilal
- Sarra AyouniSASarra Ayouni
- Gridsada PhanomchoengGridsada Phanomchoeng
Open Access
- 11 October 2025
- journal article
- Published by Elsevier in Alexandria Engineering Journal
- Vol. 131, 183-198
Abstract
No abstract availableFunding Information
- Chulalongkorn University (IND_FF_68_007_2100_001)
This publication has 24 references indexed in Scilit:
- Robotic inspection for autonomous crack segmentation and exploration using deep reinforcement learningAutomation in Construction, 2025
- Enhancing driver attention and road safety through EEG-informed deep reinforcement learning and soft computingApplied Soft Computing, 2024
- Deep learning-based intelligent detection of pavement distressAutomation in Construction, 2024
- Smart monitoring of road pavement deformations from UAV images by using machine learningInnovative Infrastructure Solutions, 2023
- Dual-path network combining CNN and transformer for pavement crack segmentationAutomation in Construction, 2023
- SwinCrack: Pavement crack detection using convolutional swin-transformer networkDigital Signal Processing, 2023
- Advanced crack detection and segmentation on bridge decks using deep learningConstruction and Building Materials, 2023
- A novel transformer-based network with attention mechanism for automatic pavement crack detectionConstruction and Building Materials, 2023
- Pavement anomaly detection based on transformer and self-supervised learningAutomation in Construction, 2022
- Automated object detection on aerial images for limited capacity embedded device using a lightweight CNN modelAlexandria Engineering Journal, 2022