Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder

Convolutional neural networks perform impressively in complicated computer-vision image-segmentation tasks. Vision-based systems surpass humans in speed and accuracy in quality inspection tasks. Moreover, the maintenance of big infrastructures, such as roads, bridges, or buildings, is tedious and ti...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Sensors (Basel, Switzerland) Ročník 20; číslo 9; s. 2557
Hlavní autoři: Augustauskas, Rytis, Lipnickas, Arūnas
Médium: Journal Article
Jazyk:angličtina
Vydáno: Switzerland MDPI 30.04.2020
MDPI AG
Témata:
ISSN:1424-8220, 1424-8220
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Convolutional neural networks perform impressively in complicated computer-vision image-segmentation tasks. Vision-based systems surpass humans in speed and accuracy in quality inspection tasks. Moreover, the maintenance of big infrastructures, such as roads, bridges, or buildings, is tedious and time-demanding work. In this research, we addressed pavement-quality evaluation by pixelwise defect segmentation using a U-Net deep autoencoder. Additionally, to the original neural network architecture, we utilized residual connections, atrous spatial pyramid pooling with parallel and “Waterfall” connections, and attention gates to perform better defect extraction. The proposed neural network configurations showed a segmentation performance improvement over U-Net with no significant computational overhead. Statistical and visual performance evaluation was taken into consideration for the model comparison. Experiments were conducted on CrackForest, Crack500, GAPs384, and mixed datasets.
AbstractList Convolutional neural networks perform impressively in complicated computer-vision image-segmentation tasks. Vision-based systems surpass humans in speed and accuracy in quality inspection tasks. Moreover, the maintenance of big infrastructures, such as roads, bridges, or buildings, is tedious and time-demanding work. In this research, we addressed pavement-quality evaluation by pixelwise defect segmentation using a U-Net deep autoencoder. Additionally, to the original neural network architecture, we utilized residual connections, atrous spatial pyramid pooling with parallel and “Waterfall” connections, and attention gates to perform better defect extraction. The proposed neural network configurations showed a segmentation performance improvement over U-Net with no significant computational overhead. Statistical and visual performance evaluation was taken into consideration for the model comparison. Experiments were conducted on CrackForest, Crack500, GAPs384, and mixed datasets.
Convolutional neural networks perform impressively in complicated computer-vision image-segmentation tasks. Vision-based systems surpass humans in speed and accuracy in quality inspection tasks. Moreover, the maintenance of big infrastructures, such as roads, bridges, or buildings, is tedious and time-demanding work. In this research, we addressed pavement-quality evaluation by pixelwise defect segmentation using a U-Net deep autoencoder. Additionally, to the original neural network architecture, we utilized residual connections, atrous spatial pyramid pooling with parallel and "Waterfall" connections, and attention gates to perform better defect extraction. The proposed neural network configurations showed a segmentation performance improvement over U-Net with no significant computational overhead. Statistical and visual performance evaluation was taken into consideration for the model comparison. Experiments were conducted on CrackForest, Crack500, GAPs384, and mixed datasets.Convolutional neural networks perform impressively in complicated computer-vision image-segmentation tasks. Vision-based systems surpass humans in speed and accuracy in quality inspection tasks. Moreover, the maintenance of big infrastructures, such as roads, bridges, or buildings, is tedious and time-demanding work. In this research, we addressed pavement-quality evaluation by pixelwise defect segmentation using a U-Net deep autoencoder. Additionally, to the original neural network architecture, we utilized residual connections, atrous spatial pyramid pooling with parallel and "Waterfall" connections, and attention gates to perform better defect extraction. The proposed neural network configurations showed a segmentation performance improvement over U-Net with no significant computational overhead. Statistical and visual performance evaluation was taken into consideration for the model comparison. Experiments were conducted on CrackForest, Crack500, GAPs384, and mixed datasets.
Author Augustauskas, Rytis
Lipnickas, Arūnas
AuthorAffiliation Department of Automation, Kaunas University of Technology, 51367 Kaunas, Lithuania; arunas.lipnickas@ktu.lt
AuthorAffiliation_xml – name: Department of Automation, Kaunas University of Technology, 51367 Kaunas, Lithuania; arunas.lipnickas@ktu.lt
Author_xml – sequence: 1
  givenname: Rytis
  surname: Augustauskas
  fullname: Augustauskas, Rytis
– sequence: 2
  givenname: Arūnas
  orcidid: 0000-0002-5686-0646
  surname: Lipnickas
  fullname: Lipnickas, Arūnas
BackLink https://www.ncbi.nlm.nih.gov/pubmed/32365925$$D View this record in MEDLINE/PubMed
BookMark eNptkUtv1DAURi3Uij5gwR9AWcIi1PZ17GSDVLU8Bo3USqVry7GvB1dJPNiZEfx7XKaMWtSVX-eea_s7IQdTnJCQN4x-AOjoWeaUdrxp1AtyzAQXdcs5PXg0PyInOd9RygGgfUmOgINsSsUx-bYY1ylu0VXX4RcO9RK3OFTXZosjTnN9iR7tXN3g6n5p5hCn6jaHaVWZ6hJxXZ1v5oiTjQ7TK3LozZDx9cN4Sm4_f_p-8bVeXn1ZXJwvaysEm-tW9YhOdp6zvmUeHG_ahluFXkKrqBNdD7bnKJVxDICytu9QeU-NEo57gFOy2HldNHd6ncJo0m8dTdB_N2JaaZPmYAfUQBslJZRvcCAcFT1vTCfRU-ul8EoV18eda73pR3S2PDKZ4Yn06ckUfuhV3GrFRcdUWwTvHgQp_txgnvUYssVhMBPGTdYculZCQVlB3z7utW_yL4wCvN8BNsWcE_o9wqi-D1rvgy7s2X-sDbt8yjXD8EzFH6FpqPw
CitedBy_id crossref_primary_10_1016_j_autcon_2023_105186
crossref_primary_10_1088_1361_6501_ada0d0
crossref_primary_10_1016_j_autcon_2023_104853
crossref_primary_10_3390_s24165205
crossref_primary_10_1109_TITS_2024_3385788
crossref_primary_10_1111_mice_13128
crossref_primary_10_3390_math10224351
crossref_primary_10_1007_s41062_024_01733_w
crossref_primary_10_1016_j_measurement_2021_109900
crossref_primary_10_1155_jece_2935790
crossref_primary_10_1109_TIM_2025_3550234
crossref_primary_10_1109_TITS_2023_3348812
crossref_primary_10_1016_j_autcon_2021_103912
crossref_primary_10_1108_SASBE_09_2023_0251
crossref_primary_10_1155_2022_1822585
crossref_primary_10_1155_2022_8965842
crossref_primary_10_1109_ACCESS_2021_3052224
crossref_primary_10_1109_TITS_2024_3436015
crossref_primary_10_1109_JSEN_2023_3298777
crossref_primary_10_3390_jimaging9070138
crossref_primary_10_32604_cmc_2024_057213
crossref_primary_10_1111_mice_12844
crossref_primary_10_3390_a13080198
crossref_primary_10_1007_s00371_022_02442_0
crossref_primary_10_3390_s21072262
crossref_primary_10_1016_j_autcon_2022_104664
crossref_primary_10_3390_s20123405
crossref_primary_10_1007_s00371_024_03531_y
crossref_primary_10_12677_JISP_2023_123032
crossref_primary_10_1007_s11694_024_02466_1
crossref_primary_10_1109_ACCESS_2021_3116799
crossref_primary_10_3390_rs13010056
crossref_primary_10_1109_TITS_2022_3177210
crossref_primary_10_3390_a16120568
crossref_primary_10_1186_s40537_024_00981_y
crossref_primary_10_1007_s00371_024_03409_z
crossref_primary_10_3390_rs15071750
crossref_primary_10_1016_j_autcon_2025_106203
crossref_primary_10_1109_LGRS_2021_3129607
crossref_primary_10_1016_j_autcon_2024_105497
crossref_primary_10_1016_j_autcon_2024_105297
crossref_primary_10_1007_s00170_021_08399_z
crossref_primary_10_1016_j_autcon_2023_105192
crossref_primary_10_1109_TIM_2023_3284050
crossref_primary_10_3390_rs14153625
crossref_primary_10_32604_cmc_2023_042183
crossref_primary_10_3390_machines12040276
crossref_primary_10_1016_j_autcon_2024_105896
crossref_primary_10_1109_TITS_2024_3424525
crossref_primary_10_1016_j_engappai_2024_109175
crossref_primary_10_1016_j_aej_2025_03_072
crossref_primary_10_1080_10298436_2022_2086692
crossref_primary_10_1177_03611981251322484
crossref_primary_10_1155_2022_7733196
Cites_doi 10.1109/TSMC.1979.4310076
10.1016/j.media.2019.01.012
10.1109/ITME.2018.00080
10.1061/(ASCE)0887-3801(1999)13:4(270)
10.1109/ICCV.2015.123
10.1109/IGARSS.2019.8900625
10.1109/IDAACS.2019.8924337
10.1109/ICARCV.2018.8581341
10.1109/EIT.2011.5978575
10.2307/1932409
10.3390/s18113717
10.3390/app9224804
10.1016/j.cviu.2017.03.007
10.1109/TITS.2016.2552248
10.1109/IJCNN.2019.8852257
10.3390/rs11010020
10.1109/IJCNN.2017.7966101
10.1109/TITS.2019.2910595
10.1109/ACCESS.2020.3003638
10.5220/0007698800002108
10.3390/data3030028
10.1007/978-3-319-24474-7_14
10.1007/978-3-319-24574-4_28
10.3390/s19245361
10.1007/s10489-018-01396-y
10.1109/CVPR.2016.90
10.1111/j.1467-8667.2011.00736.x
10.3390/app9091816
10.1109/IVS.2019.8814000
10.1155/2019/1813763
10.1109/BEC.2010.5630750
10.3390/app9224829
10.1007/s41315-017-0031-9
10.1016/j.aei.2011.01.002
10.1109/ACCESS.2020.2966881
10.1109/SIPROCESS.2019.8868690
10.1109/TPAMI.2017.2699184
10.1007/978-3-030-01234-2_49
10.1016/B978-0-12-266722-0.50016-6
10.1109/ICIP.2016.7533052
10.1109/ACCESS.2019.2940767
10.1109/MELCON.2008.4618541
10.1007/s11042-017-4440-4
ContentType Journal Article
Copyright 2020 by the authors. 2020
Copyright_xml – notice: 2020 by the authors. 2020
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3390/s20092557
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
CrossRef
PubMed

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1424-8220
ExternalDocumentID oai_doaj_org_article_3057663424d34d04b25a96ef0cf64f77
PMC7249178
32365925
10_3390_s20092557
Genre Journal Article
GroupedDBID ---
123
2WC
53G
5VS
7X7
88E
8FE
8FG
8FI
8FJ
AADQD
AAHBH
AAYXX
ABDBF
ABUWG
ACUHS
ADBBV
ADMLS
AENEX
AFFHD
AFKRA
AFZYC
ALMA_UNASSIGNED_HOLDINGS
BENPR
BPHCQ
BVXVI
CCPQU
CITATION
CS3
D1I
DU5
E3Z
EBD
ESX
F5P
FYUFA
GROUPED_DOAJ
GX1
HH5
HMCUK
HYE
KQ8
L6V
M1P
M48
MODMG
M~E
OK1
OVT
P2P
P62
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQQKQ
PROAC
PSQYO
RNS
RPM
TUS
UKHRP
XSB
~8M
3V.
ABJCF
ALIPV
ARAPS
HCIFZ
KB.
M7S
NPM
PDBOC
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c441t-87beed69f21b81f3d25852c7ef63870d49b3cb2e67ad133018b9e7ff0a74d2f33
IEDL.DBID DOA
ISICitedReferencesCount 62
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000537106200121&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1424-8220
IngestDate Fri Oct 03 12:40:50 EDT 2025
Tue Nov 04 02:00:47 EST 2025
Thu Sep 04 19:13:29 EDT 2025
Wed Feb 19 02:31:36 EST 2025
Sat Nov 29 07:15:07 EST 2025
Tue Nov 18 21:44:36 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 9
Keywords deep learning
pavement defects
atrous spatial pyramid pooling
CNN (Convolutional neural networks)
residual connection
attention gate
Language English
License Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c441t-87beed69f21b81f3d25852c7ef63870d49b3cb2e67ad133018b9e7ff0a74d2f33
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-5686-0646
OpenAccessLink https://doaj.org/article/3057663424d34d04b25a96ef0cf64f77
PMID 32365925
PQID 2398639171
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_3057663424d34d04b25a96ef0cf64f77
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7249178
proquest_miscellaneous_2398639171
pubmed_primary_32365925
crossref_primary_10_3390_s20092557
crossref_citationtrail_10_3390_s20092557
PublicationCentury 2000
PublicationDate 20200430
PublicationDateYYYYMMDD 2020-04-30
PublicationDate_xml – month: 4
  year: 2020
  text: 20200430
  day: 30
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Sensors (Basel, Switzerland)
PublicationTitleAlternate Sensors (Basel)
PublicationYear 2020
Publisher MDPI
MDPI AG
Publisher_xml – name: MDPI
– name: MDPI AG
References ref_50
ref_14
ref_58
ref_13
ref_12
ref_56
ref_55
ref_10
ref_53
ref_52
ref_19
ref_17
ref_15
ref_59
Wu (ref_22) 2018; 77
ref_61
Cord (ref_11) 2012; 27
Nisanth (ref_8) 2014; 6
Stutz (ref_51) 2018; 166
ref_21
ref_20
Li (ref_23) 2019; 2019
ref_63
ref_62
Cao (ref_4) 2020; 8
Escalona (ref_57) 2019; 23
ref_29
ref_28
Loupos (ref_24) 2018; 2
ref_27
ref_26
Shi (ref_16) 2016; 17
Wu (ref_54) 2019; 7
Cheng (ref_49) 1999; 13
Otsu (ref_9) 1979; 9
ref_36
ref_35
ref_34
Protopapadakis (ref_25) 2019; 49
ref_33
Chen (ref_37) 2018; 40
ref_32
ref_31
ref_30
Schlemper (ref_47) 2019; 53
ref_39
Koch (ref_6) 2011; 25
ref_38
Dice (ref_60) 1945; 26
ref_46
ref_45
ref_44
ref_43
ref_42
ref_41
ref_40
ref_1
ref_3
ref_2
Yang (ref_18) 2020; 21
ref_48
ref_5
ref_7
References_xml – volume: 9
  start-page: 62
  year: 1979
  ident: ref_9
  article-title: A Threshold Selection Method from Gray-Level Histograms
  publication-title: IEEE Trans. Syst. Man Cybern.
  doi: 10.1109/TSMC.1979.4310076
– volume: 53
  start-page: 197
  year: 2019
  ident: ref_47
  article-title: Attention gated networks: Learning to leverage salient regions in medical images
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2019.01.012
– ident: ref_32
  doi: 10.1109/ITME.2018.00080
– volume: 23
  start-page: 451
  year: 2019
  ident: ref_57
  article-title: Fully convolutional networks for automatic pavement crack segmentation
  publication-title: Comput. Sist.
– volume: 13
  start-page: 270
  year: 1999
  ident: ref_49
  article-title: Novel Approach to Pavement Cracking Detection Based on Fuzzy Set Theory
  publication-title: J. Comput. Civ. Eng.
  doi: 10.1061/(ASCE)0887-3801(1999)13:4(270)
– ident: ref_28
  doi: 10.1109/ICCV.2015.123
– ident: ref_31
  doi: 10.1109/IGARSS.2019.8900625
– ident: ref_26
  doi: 10.1109/IDAACS.2019.8924337
– ident: ref_39
– ident: ref_62
  doi: 10.1109/ICARCV.2018.8581341
– ident: ref_7
  doi: 10.1109/EIT.2011.5978575
– volume: 26
  start-page: 297
  year: 1945
  ident: ref_60
  article-title: Measures of the Amount of Ecologic Association Between Species
  publication-title: Ecology
  doi: 10.2307/1932409
– ident: ref_42
  doi: 10.3390/s18113717
– ident: ref_3
  doi: 10.3390/app9224804
– volume: 166
  start-page: 1
  year: 2018
  ident: ref_51
  article-title: Superpixels: An evaluation of the state-of-the-art
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2017.03.007
– ident: ref_61
– ident: ref_58
– volume: 17
  start-page: 3434
  year: 2016
  ident: ref_16
  article-title: Automatic road crack detection using random structured forests
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2016.2552248
– ident: ref_21
  doi: 10.1109/IJCNN.2019.8852257
– ident: ref_40
  doi: 10.3390/rs11010020
– ident: ref_56
– ident: ref_27
– ident: ref_52
– ident: ref_20
  doi: 10.1109/IJCNN.2017.7966101
– ident: ref_48
– volume: 21
  start-page: 1525
  year: 2020
  ident: ref_18
  article-title: Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2019.2910595
– ident: ref_38
– ident: ref_55
  doi: 10.1109/ACCESS.2020.3003638
– ident: ref_43
  doi: 10.5220/0007698800002108
– ident: ref_59
– ident: ref_1
  doi: 10.3390/data3030028
– ident: ref_17
  doi: 10.1007/978-3-319-24474-7_14
– ident: ref_53
– ident: ref_30
– ident: ref_15
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref_45
  doi: 10.3390/s19245361
– volume: 49
  start-page: 2793
  year: 2019
  ident: ref_25
  article-title: Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing
  publication-title: Appl. Intell.
  doi: 10.1007/s10489-018-01396-y
– ident: ref_35
  doi: 10.1109/CVPR.2016.90
– volume: 27
  start-page: 244
  year: 2012
  ident: ref_11
  article-title: Automatic Road Defect Detection by Textural Pattern Recognition Based on AdaBoost
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/j.1467-8667.2011.00736.x
– ident: ref_41
  doi: 10.3390/app9091816
– ident: ref_19
  doi: 10.1109/IVS.2019.8814000
– ident: ref_14
– volume: 2019
  start-page: 1813763
  year: 2019
  ident: ref_23
  article-title: Automatic Segmentation and Enhancement of Pavement Cracks Based on 3D Pavement Images
  publication-title: J. Adv. Transp.
  doi: 10.1155/2019/1813763
– ident: ref_50
  doi: 10.1109/BEC.2010.5630750
– ident: ref_63
– ident: ref_33
  doi: 10.3390/app9224829
– volume: 2
  start-page: 43
  year: 2018
  ident: ref_24
  article-title: Autonomous robotic system for tunnel structural inspection and assessment
  publication-title: Int. J. Intell. Robot. Appl.
  doi: 10.1007/s41315-017-0031-9
– volume: 25
  start-page: 507
  year: 2011
  ident: ref_6
  article-title: Pothole detection in asphalt pavement images
  publication-title: Adv. Eng. Inform.
  doi: 10.1016/j.aei.2011.01.002
– ident: ref_29
– volume: 8
  start-page: 14531
  year: 2020
  ident: ref_4
  article-title: Review of pavement defect detection methods
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2966881
– ident: ref_2
– ident: ref_34
  doi: 10.1109/SIPROCESS.2019.8868690
– ident: ref_46
– ident: ref_12
– volume: 6
  start-page: 14
  year: 2014
  ident: ref_8
  article-title: Automated Visual Inspection of Pavement Crack Detection and Characterization
  publication-title: Int. J. Technol. Eng. Syst.
– volume: 40
  start-page: 834
  year: 2018
  ident: ref_37
  article-title: DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2017.2699184
– ident: ref_44
  doi: 10.1007/978-3-030-01234-2_49
– ident: ref_10
  doi: 10.1016/B978-0-12-266722-0.50016-6
– ident: ref_13
  doi: 10.1109/ICIP.2016.7533052
– ident: ref_36
– volume: 7
  start-page: 130032
  year: 2019
  ident: ref_54
  article-title: Sample and Structure-Guided Network for Road Crack Detection
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2940767
– ident: ref_5
  doi: 10.1109/MELCON.2008.4618541
– volume: 77
  start-page: 10437
  year: 2018
  ident: ref_22
  article-title: Deep residual learning for image steganalysis
  publication-title: Multimed. Tools Appl.
  doi: 10.1007/s11042-017-4440-4
SSID ssj0023338
Score 2.546979
Snippet Convolutional neural networks perform impressively in complicated computer-vision image-segmentation tasks. Vision-based systems surpass humans in speed and...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 2557
SubjectTerms atrous spatial pyramid pooling
attention gate
CNN (Convolutional neural networks)
deep learning
pavement defects
residual connection
Title Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder
URI https://www.ncbi.nlm.nih.gov/pubmed/32365925
https://www.proquest.com/docview/2398639171
https://pubmed.ncbi.nlm.nih.gov/PMC7249178
https://doaj.org/article/3057663424d34d04b25a96ef0cf64f77
Volume 20
WOSCitedRecordID wos000537106200121&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: DOA
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: M~E
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: BENPR
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Health & Medical
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: 7X7
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Publicly Available Content Database
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: PIMPY
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwEB7BwgEOiDflUQXEgUu0ie3E8XGX7QoQW0U8pHKK_BgvlZZ01aaIE7-dsZNWLVqJCxcfHCuxZuzMfJ7xNwCvlbBOuoKnqpA6HN3Y1FSh0SL3ghmvlYnFJuR0Ws1mqt4p9RVywnp64F5wh7QeJVlFwYTjwmXCsEKrEn1mfSm8jPfIM6k2YGqAWpyQV88jxAnUH64it1ARbNCO9Ykk_Vd5ln8nSO5YnNO7cGdwFZOjfor34Bq29-H2DoHgA_jQnwmgS-r5L7xIP4YUoKTWkQS8S08wJGskn_H8x3DFqE1ijkCikxPEy-Ro3S0Ck6XD5UP4ejr58vZdOlRHSC25MB39xgzZt1J5lpsq99wx8vyZlehpS8nMCWW4NQxLqR0B0SyvjELpfaalcMxz_ggO2kWLTyCRtkQsyVVyTgmvikrTey0WBCeYkRZH8GYjtcYO1OGhgsVFQxAiCLjZCngEr7ZDL3u-jKsGHQfRbwcEiuvYQYpvBsU3_1L8CF5uFNfQlghxDt3iYr1qAqUhOV65zEfwuFfk9lOc8RBILkYg91S8N5f9J-38e6TdloRUc1k9_R-Tfwa3WADuMSz1HA665RpfwE37s5uvlmO4LmcyttUYbhxPpvWncVzf1J79nlBf_f6s_vYHVkX_1Q
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Improved+Pixel-Level+Pavement-Defect+Segmentation+Using+a+Deep+Autoencoder&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Rytis+Augustauskas&rft.au=Ar%C5%ABnas+Lipnickas&rft.date=2020-04-30&rft.pub=MDPI+AG&rft.eissn=1424-8220&rft.volume=20&rft.issue=9&rft.spage=2557&rft_id=info:doi/10.3390%2Fs20092557&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_3057663424d34d04b25a96ef0cf64f77
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon