Submit

Login Login

Register Register

Home / Journals / SDHM / Online First / doi:10.32604/sdhm.2024.042388
Journal Menu
Special lssues
Table of Content

All issues

Online First

2024

2023

2022

2021

2020

2019

2018

2017

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

Open Access

ARTICLE

Rapid and Accurate Identification of Concrete Surface Cracks via a Lightweight & Efficient YOLOv3 Algorithm

Haoan Gu1, Kai Zhu1, Alfred Strauss2, Yehui Shi3,4, Dragoslav Sumarac5, Maosen Cao1,*
1 College of Mechanics and Engineering Science, Hohai University, Nanjing, 211100, China
2 Department of Civil Engineering and Natural Hazards, University of Natural Resources and Life Sciences, Vienna, 1180, Austria
3 The First Geological Brigade of the Bureau of Geology and Mineral Resources of Jiangsu, Nanjing, 210041, China
4 Control Technology Group Co., Nanjing, 210041, China
5 Department of Technical Sciences, Civil Engineering, State University of Novi Pazar, Novi Pazar, 36300, Serbia
* Corresponding Author: Maosen Cao. Email: cmszhy@hhu.edu.cn

Structural Durability & Health Monitoring https://doi.org/10.32604/sdhm.2024.042388

Received 28 May 2023; Accepted 01 November 2023; Published online 18 April 2024

Abstract

Concrete materials and structures are extensively used in transformation infrastructure and they usually bear cracks during their long-term operation. Detecting cracks using deep-learning algorithms like YOLOv3 (You Only Look Once version 3) is a new trend to pursue intelligent detection of concrete surface cracks. YOLOv3 is a typical deep-learning algorithm used for object detection. Owing to its generality, YOLOv3 lacks specific effi- ciency and accuracy in identifying concrete surface cracks. An improved algorithm based on YOLOv3, specialized in the rapid and accurate identification of concrete surface cracks is worthy of investigation. This study proposes a tailored deep-learning algorithm, termed MDN-YOLOv3 (MDN: multi-dilated network), of which the MDN is formulated based on three retrofit techniques, and it provides a new backbone network for YOLOv3. The three specific retrofit techniques are briefed: (i) Depthwise separable convolution is utilized to reduce the size of the backbone network; (ii) The dilated-down sampling structure is proposed and used in the backbone network to achieve multi-scale feature fusion; and (iii) The convolutional block attention module is introduced to enhance feature extraction ability. Results show that the proposed MDN-YOLOv3 is 97.2% smaller and 41.5% faster than YOLOv3 in identifying concrete surface cracks, forming a lightweight & efficient YOLOv3 algorithm for intelligently identifying concrete surface cracks.

Keywords

YOLOv3; concrete crack identification; MDN-YOLOv3; optimization retrofit techniques; depthwise separable convolution; dilated-down sampling; attention mechanism

  • 84

    View

  • 18

    Download

  • 0

    Like

Related articles
Copyright© 2024 Tech Science Press
© 1997-2024 TSP (Henderson, USA) unless otherwise stated

Share Link