Parallel Systems for the Bridge Inspection

As the number of bridges grows in China, bridge inspection is necessary to ensure public transport safety. With the development of various technologies in recent years, such as unmanned aerial vehicles, computer vision, advanced sensing, artificial intelligence, intelligent technologies in bridge in...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of radio frequency identification (Online) 2022, Vol.6, p.783-786
Main Authors: Ma, Hongyao, Wang, Zhixue, Gao, Hang, Shen, Zhen, Zhang, Hong, Hu, Xueliang, Li, Chuanfu, Xiong, Gang
Format: Article
Language:English
Subjects:
Artificial intelligence
Bridge inspection
Bridges
Classification
Computational modeling
Computer vision
Datasets
Inspection
Intelligent systems
intelligent technologies
Load modeling
Neural networks
Parallel systems
Point cloud compression
Public transportation
Simultaneous localization and mapping
Transportation safety
Unmanned aerial vehicles
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As the number of bridges grows in China, bridge inspection is necessary to ensure public transport safety. With the development of various technologies in recent years, such as unmanned aerial vehicles, computer vision, advanced sensing, artificial intelligence, intelligent technologies in bridge inspection have developed rapidly and are gradually replacing traditional methods. Here we propose the parallel systems for bridge inspection, which introduces the parallel theory into the field of bridge inspection to solve the problems of data shortage and the special scene prediction. Based on the classification of concrete dataset (CCD) and the parallel classification dataset (PCD), ConvNeXt and other neural networks are trained and compared. The crack detection accuracy reached 99.22%. We believe that the framework proposed in this paper can improve the efficiency and accuracy of bridge inspection significantly.
ISSN:2469-7281
2469-729X
DOI:10.1109/JRFID.2022.3212598