Semantic-Segmentation-Based Rail Fastener State Recognition Algorithm
Rail fastener status recognition and detection are key steps in the inspection of the rail area status and function of real engineering projects. With the development of and widespread interest in image processing techniques and deep learning theory, detection methods that combine the two have yield...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2021-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2021/8956164 |
id |
doaj-a78fed54b09d4b17be32c62e11754c3b |
---|---|
record_format |
Article |
spelling |
doaj-a78fed54b09d4b17be32c62e11754c3b2021-03-15T00:01:18ZengHindawi LimitedMathematical Problems in Engineering1563-51472021-01-01202110.1155/2021/8956164Semantic-Segmentation-Based Rail Fastener State Recognition AlgorithmLiming Li0Rui Sun1Shuguang Zhao2Xiaodong Chai3Shubin Zheng4Ruichao Shen5School of Information Science and TechnologySchool of Urban Railway TransportationSchool of Information Science and TechnologySchool of Urban Railway TransportationSchool of Urban Railway TransportationSchool of Urban Railway TransportationRail fastener status recognition and detection are key steps in the inspection of the rail area status and function of real engineering projects. With the development of and widespread interest in image processing techniques and deep learning theory, detection methods that combine the two have yielded promising results in practical detection applications. In this paper, a semantic-segmentation-based algorithm for the state recognition of rail fasteners is proposed. On the one hand, we propose a functional area location and annotation method based on a salient detection model and construct a novel slab-fastclip-type rail fastener dataset. On the other hand, we propose a semantic-segmentation-framework-based model for rail fastener detection, where we detect and classify rail fastener states by combining the pyramid scene analysis network (PSPNet) and vector geometry measurements. Experimental results prove the validity and superiority of the proposed method, which can be introduced into practical engineering projects.http://dx.doi.org/10.1155/2021/8956164 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Liming Li Rui Sun Shuguang Zhao Xiaodong Chai Shubin Zheng Ruichao Shen |
spellingShingle |
Liming Li Rui Sun Shuguang Zhao Xiaodong Chai Shubin Zheng Ruichao Shen Semantic-Segmentation-Based Rail Fastener State Recognition Algorithm Mathematical Problems in Engineering |
author_facet |
Liming Li Rui Sun Shuguang Zhao Xiaodong Chai Shubin Zheng Ruichao Shen |
author_sort |
Liming Li |
title |
Semantic-Segmentation-Based Rail Fastener State Recognition Algorithm |
title_short |
Semantic-Segmentation-Based Rail Fastener State Recognition Algorithm |
title_full |
Semantic-Segmentation-Based Rail Fastener State Recognition Algorithm |
title_fullStr |
Semantic-Segmentation-Based Rail Fastener State Recognition Algorithm |
title_full_unstemmed |
Semantic-Segmentation-Based Rail Fastener State Recognition Algorithm |
title_sort |
semantic-segmentation-based rail fastener state recognition algorithm |
publisher |
Hindawi Limited |
series |
Mathematical Problems in Engineering |
issn |
1563-5147 |
publishDate |
2021-01-01 |
description |
Rail fastener status recognition and detection are key steps in the inspection of the rail area status and function of real engineering projects. With the development of and widespread interest in image processing techniques and deep learning theory, detection methods that combine the two have yielded promising results in practical detection applications. In this paper, a semantic-segmentation-based algorithm for the state recognition of rail fasteners is proposed. On the one hand, we propose a functional area location and annotation method based on a salient detection model and construct a novel slab-fastclip-type rail fastener dataset. On the other hand, we propose a semantic-segmentation-framework-based model for rail fastener detection, where we detect and classify rail fastener states by combining the pyramid scene analysis network (PSPNet) and vector geometry measurements. Experimental results prove the validity and superiority of the proposed method, which can be introduced into practical engineering projects. |
url |
http://dx.doi.org/10.1155/2021/8956164 |
work_keys_str_mv |
AT limingli semanticsegmentationbasedrailfastenerstaterecognitionalgorithm AT ruisun semanticsegmentationbasedrailfastenerstaterecognitionalgorithm AT shuguangzhao semanticsegmentationbasedrailfastenerstaterecognitionalgorithm AT xiaodongchai semanticsegmentationbasedrailfastenerstaterecognitionalgorithm AT shubinzheng semanticsegmentationbasedrailfastenerstaterecognitionalgorithm AT ruichaoshen semanticsegmentationbasedrailfastenerstaterecognitionalgorithm |
_version_ |
1714785241236766720 |