A review of deep learning methods for pixel-level crack detection
Cracks are a major sign of aging transportation infrastructure. The detection and repair of cracks is the key to ensuring the overall safety of the transportation infrastructure. In recent years, due to the remarkable success of deep learning (DL) in the field of crack detection, many researches hav...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2022-12-01
|
Series: | Journal of Traffic and Transportation Engineering (English ed. Online) |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2095756422001027 |
_version_ | 1797961017025626112 |
---|---|
author | Hongxia Li Weixing Wang Mengfei Wang Limin Li Vivian Vimlund |
author_facet | Hongxia Li Weixing Wang Mengfei Wang Limin Li Vivian Vimlund |
author_sort | Hongxia Li |
collection | DOAJ |
description | Cracks are a major sign of aging transportation infrastructure. The detection and repair of cracks is the key to ensuring the overall safety of the transportation infrastructure. In recent years, due to the remarkable success of deep learning (DL) in the field of crack detection, many researches have been devoted to developing pixel-level crack image segmentation (CIS) models based on DL to improve crack detection accuracy, but as far as we know there is no review of DL-based CIS methods yet. To address this gap, we present a comprehensive thematic survey of DL-based CIS techniques. Our review offers several contributions to the CIS area. First, more than 40 papers of journal or top conference most published in the last three years are identified and collected based on the systematic literature review method. Second, according to the backbone network architecture of the models proposed in them, they are grouped into 10 topics: FCN, U-Net, encoder-decoder model, multi-scale, attention mechanism, transformer, two-stage detection, multi-modal fusion, unsupervised learning and weakly supervised learning, to be reviewed. Meanwhile, our survey focuses on discussing strengths and limitations of the models in each topic so as to reveal the latest research progress in the CIS field. Third, publicly accessible data sets, evaluation metrics, and loss functions that can be used for pixel-level crack detection are systematically introduced and summarized to facilitate researchers to select suitable components according to their own research tasks. Finally, we discuss six common problems and existing solutions to them in the field of DL-based CIS, and then suggest eight possible future research directions in this field. |
first_indexed | 2024-04-11T00:53:53Z |
format | Article |
id | doaj.art-f483a6234cd2408880749243a0f8e982 |
institution | Directory Open Access Journal |
issn | 2095-7564 |
language | English |
last_indexed | 2024-04-11T00:53:53Z |
publishDate | 2022-12-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Journal of Traffic and Transportation Engineering (English ed. Online) |
spelling | doaj.art-f483a6234cd2408880749243a0f8e9822023-01-05T08:36:37ZengKeAi Communications Co., Ltd.Journal of Traffic and Transportation Engineering (English ed. Online)2095-75642022-12-0196945968A review of deep learning methods for pixel-level crack detectionHongxia Li0Weixing Wang1Mengfei Wang2Limin Li3Vivian Vimlund4School of Information Engineering, Chang'an University, Xi'an 710064, China; School of Computer, Baoji University of Arts and Sciences, Baoji 721013, ChinaSchool of Information Engineering, Chang'an University, Xi'an 710064, China; Corresponding author. Tel.: +86 29 82334562School of Information Engineering, Chang'an University, Xi'an 710064, ChinaSchool of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, China; Corresponding author.Department of Computer Science and Technology, Linkoping University, Linköping, SwedenCracks are a major sign of aging transportation infrastructure. The detection and repair of cracks is the key to ensuring the overall safety of the transportation infrastructure. In recent years, due to the remarkable success of deep learning (DL) in the field of crack detection, many researches have been devoted to developing pixel-level crack image segmentation (CIS) models based on DL to improve crack detection accuracy, but as far as we know there is no review of DL-based CIS methods yet. To address this gap, we present a comprehensive thematic survey of DL-based CIS techniques. Our review offers several contributions to the CIS area. First, more than 40 papers of journal or top conference most published in the last three years are identified and collected based on the systematic literature review method. Second, according to the backbone network architecture of the models proposed in them, they are grouped into 10 topics: FCN, U-Net, encoder-decoder model, multi-scale, attention mechanism, transformer, two-stage detection, multi-modal fusion, unsupervised learning and weakly supervised learning, to be reviewed. Meanwhile, our survey focuses on discussing strengths and limitations of the models in each topic so as to reveal the latest research progress in the CIS field. Third, publicly accessible data sets, evaluation metrics, and loss functions that can be used for pixel-level crack detection are systematically introduced and summarized to facilitate researchers to select suitable components according to their own research tasks. Finally, we discuss six common problems and existing solutions to them in the field of DL-based CIS, and then suggest eight possible future research directions in this field.http://www.sciencedirect.com/science/article/pii/S2095756422001027Crack image segmentationCrack detectionConvolutional neural networksDeep learningSystematic literature review |
spellingShingle | Hongxia Li Weixing Wang Mengfei Wang Limin Li Vivian Vimlund A review of deep learning methods for pixel-level crack detection Journal of Traffic and Transportation Engineering (English ed. Online) Crack image segmentation Crack detection Convolutional neural networks Deep learning Systematic literature review |
title | A review of deep learning methods for pixel-level crack detection |
title_full | A review of deep learning methods for pixel-level crack detection |
title_fullStr | A review of deep learning methods for pixel-level crack detection |
title_full_unstemmed | A review of deep learning methods for pixel-level crack detection |
title_short | A review of deep learning methods for pixel-level crack detection |
title_sort | review of deep learning methods for pixel level crack detection |
topic | Crack image segmentation Crack detection Convolutional neural networks Deep learning Systematic literature review |
url | http://www.sciencedirect.com/science/article/pii/S2095756422001027 |
work_keys_str_mv | AT hongxiali areviewofdeeplearningmethodsforpixellevelcrackdetection AT weixingwang areviewofdeeplearningmethodsforpixellevelcrackdetection AT mengfeiwang areviewofdeeplearningmethodsforpixellevelcrackdetection AT liminli areviewofdeeplearningmethodsforpixellevelcrackdetection AT vivianvimlund areviewofdeeplearningmethodsforpixellevelcrackdetection AT hongxiali reviewofdeeplearningmethodsforpixellevelcrackdetection AT weixingwang reviewofdeeplearningmethodsforpixellevelcrackdetection AT mengfeiwang reviewofdeeplearningmethodsforpixellevelcrackdetection AT liminli reviewofdeeplearningmethodsforpixellevelcrackdetection AT vivianvimlund reviewofdeeplearningmethodsforpixellevelcrackdetection |