A transformer-based deep learning method for automatic pixel-level crack detection and feature quantification

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

5 Scopus Citations
View graph of relations

Author(s)

  • Ankang Ji
  • Xiaolong Xue
  • Limao Zhang
  • Xiaowei Luo
  • Qingpeng Man

Detail(s)

Original languageEnglish
Journal / PublicationEngineering, Construction and Architectural Management
Online published28 Dec 2023
Publication statusOnline published - 28 Dec 2023

Abstract

Purpose: Crack detection of pavement is a critical task in the periodic survey. Efficient, effective and consistent tracking of the road conditions by identifying and locating crack contributes to establishing an appropriate road maintenance and repair strategy from the promptly informed managers but still remaining a significant challenge. This research seeks to propose practical solutions for targeting the automatic crack detection from images with efficient productivity and cost-effectiveness, thereby improving the pavement performance. Design/methodology/approach: This research applies a novel deep learning method named TransUnet for crack detection, which is structured based on Transformer, combined with convolutional neural networks as encoder by leveraging a global self-attention mechanism to better extract features for enhancing automatic identification. Afterward, the detected cracks are used to quantify morphological features from five indicators, such as length, mean width, maximum width, area and ratio. Those analyses can provide valuable information for engineers to assess the pavement condition with efficient productivity. Findings: In the training process, the TransUnet is fed by a crack dataset generated by the data augmentation with a resolution of 224 × 224 pixels. Subsequently, a test set containing 80 new images is used for crack detection task based on the best selected TransUnet with a learning rate of 0.01 and a batch size of 1, achieving an accuracy of 0.8927, a precision of 0.8813, a recall of 0.8904, an F1-measure and dice of 0.8813, and a Mean Intersection over Union of 0.8082, respectively. Comparisons with several state-of-the-art methods indicate that the developed approach in this research outperforms with greater efficiency and higher reliability. Originality/value: The developed approach combines TransUnet with an integrated quantification algorithm for crack detection and quantification, performing excellently in terms of comparisons and evaluation metrics, which can provide solutions with potentially serving as the basis for an automated, cost-effective pavement condition assessment scheme. © 2023, Emerald Publishing Limited.

Research Area(s)

  • Automatic crack detection, Crack feature quantification, Deep learning, Transformer, TransUnet