A Neural Network with Spatial Attention for Pixel-Level Crack Detection on Concrete Bridges

Wenpeng Ji, Yizhai Zhang, Panfeng Huang, Yuchen Yan, Qilei Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Concrete bridges play a very important role in transportation. As the main type of concrete bridges' damage, crack detection is of great significance to ensure the safety of bridges. In order to avoid the influence of subjective factors, methods based on deep learning develop rapidly. In this paper, a new network model in the form of encoder-decoder is proposed. It achieves the crack detection on pixel-level, which means that the detection results can be further quantified in the future. Meanwhile, the model proposed adds Spatial Attention to take advantage of crack's spatial characteristics. By doing this, more crack details can be found in the test results.

Original languageEnglish
Title of host publicationProceedings of 2022 IEEE 11th Data Driven Control and Learning Systems Conference, DDCLS 2022
EditorsMingxuan Sun, Zengqiang Chen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages481-486
Number of pages6
ISBN (Electronic)9781665496759
DOIs
StatePublished - 2022
Event11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022 - Emeishan, China
Duration: 3 Aug 20225 Aug 2022

Publication series

NameProceedings of 2022 IEEE 11th Data Driven Control and Learning Systems Conference, DDCLS 2022

Conference

Conference11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022
Country/TerritoryChina
CityEmeishan
Period3/08/225/08/22

Keywords

  • Bridge detection
  • Crack detection
  • Deep learning
  • Spatial Attention Mechanism

Fingerprint

Dive into the research topics of 'A Neural Network with Spatial Attention for Pixel-Level Crack Detection on Concrete Bridges'. Together they form a unique fingerprint.

Cite this