Dual attention-based deep learning network for multi-class object semantic segmentation of tunnel point clouds

Aiming to automatically segment multi-class objects on the tunnel point cloud, a deep learning network named dual attention-based point cloud network (DAPCNet) is developed in this paper to act on point clouds for segmentation. In the developed model, data normalization and feature aggregation are f...

Full description

Saved in:
Bibliographic Details
Published in:Automation in construction Vol. 156; p. 105131
Main Authors: Ji, Ankang, Zhang, Limao, Fan, Hongqin, Xue, Xiaolong, Dou, Yudan
Format: Journal Article
Language:English
Published: Elsevier B.V 01.12.2023
Subjects:
ISSN:0926-5805, 1872-7891
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Aiming to automatically segment multi-class objects on the tunnel point cloud, a deep learning network named dual attention-based point cloud network (DAPCNet) is developed in this paper to act on point clouds for segmentation. In the developed model, data normalization and feature aggregation are first processed to eliminate data discrepancies and enhance local features, after which the processed data are input into the built network layers based on the encoder-decoder architecture coupled with an improved 3D dual attention module to extract and learn features. Furthermore, a custom loss function called Facal Cross-Entropy (“FacalCE”) is designed to enhance the model's ability to extract and learn features while addressing imbalanced data distribution. To validate the effectiveness and feasibility of the developed model, a dataset of tunnel point clouds collected from a real engineering project in China is employed. The experimental results indicate that (1) the developed model has excellent performance with Mean Intersection over Union (MIoU) of 0.8597, (2) the improved 3D dual attention module and “FacalCE” contribute to the model performance, respectively, and (3) the developed model is superior to other state-of-the-art methods, such as PointNet and DGCNN. In summary, the DAPCNet model exhibits exceptional performance, offering effective and accurate results for segmenting multi-class objects within tunnel point clouds. •A deep learning method named DAPCNet is developed for 3D point cloud segmentation.•An improved 3D dual attention module is introduced to enhance model performance.•A custom loss “FacalCE” is designed to strengthen feature learning with handling data imbalance.•Conducting comparisons to examine the model performance for segmentation.•The developed method demonstrates outstanding performance, achieving an MIoU score of 0.8597 when applied to tunnel point clouds.
AbstractList Aiming to automatically segment multi-class objects on the tunnel point cloud, a deep learning network named dual attention-based point cloud network (DAPCNet) is developed in this paper to act on point clouds for segmentation. In the developed model, data normalization and feature aggregation are first processed to eliminate data discrepancies and enhance local features, after which the processed data are input into the built network layers based on the encoder-decoder architecture coupled with an improved 3D dual attention module to extract and learn features. Furthermore, a custom loss function called Facal Cross-Entropy (“FacalCE”) is designed to enhance the model's ability to extract and learn features while addressing imbalanced data distribution. To validate the effectiveness and feasibility of the developed model, a dataset of tunnel point clouds collected from a real engineering project in China is employed. The experimental results indicate that (1) the developed model has excellent performance with Mean Intersection over Union (MIoU) of 0.8597, (2) the improved 3D dual attention module and “FacalCE” contribute to the model performance, respectively, and (3) the developed model is superior to other state-of-the-art methods, such as PointNet and DGCNN. In summary, the DAPCNet model exhibits exceptional performance, offering effective and accurate results for segmenting multi-class objects within tunnel point clouds. •A deep learning method named DAPCNet is developed for 3D point cloud segmentation.•An improved 3D dual attention module is introduced to enhance model performance.•A custom loss “FacalCE” is designed to strengthen feature learning with handling data imbalance.•Conducting comparisons to examine the model performance for segmentation.•The developed method demonstrates outstanding performance, achieving an MIoU score of 0.8597 when applied to tunnel point clouds.
ArticleNumber 105131
Author Zhang, Limao
Xue, Xiaolong
Fan, Hongqin
Ji, Ankang
Dou, Yudan
Author_xml – sequence: 1
  givenname: Ankang
  surname: Ji
  fullname: Ji, Ankang
  email: ankangji@stu.hit.edu.cn
  organization: Department of Building and Real Estate, The Hong Kong Polytechnic University, Hong Kong 999077, China
– sequence: 2
  givenname: Limao
  surname: Zhang
  fullname: Zhang, Limao
  organization: School of Civil and Hydraulic Engineering, National Center of Technology Innovation for Digital Construction, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
– sequence: 3
  givenname: Hongqin
  surname: Fan
  fullname: Fan, Hongqin
  email: hongqin.fan@polyu.edu.hk
  organization: Department of Building and Real Estate, The Hong Kong Polytechnic University, Hong Kong 999077, China
– sequence: 4
  givenname: Xiaolong
  surname: Xue
  fullname: Xue, Xiaolong
  organization: School of Management, Guangzhou University, Guangzhou, Guangdong 510006, China
– sequence: 5
  givenname: Yudan
  surname: Dou
  fullname: Dou, Yudan
  organization: Department of Construction Management, Dalian University of Technology, Dalian, Liaoning 116024, China
BookMark eNqFkE1LxDAQhoOs4O7qP_CQP9A16Xc9CLJ-woIXPYd0Ml1S22RJUsV_b5Z68qCnGYZ5XmaeFVkYa5CQS842nPHyqt_IKYA1m5SlWRwVPOMnZMnrKk2quuELsmRNWiZFzYozsvK-Z4xVrGyWxNxNcqAyBDRBW5O00qOiCvFAB5TOaLOnBsOnde-0s46O0xB0AoP0ntq2RwjU4ygjDLHZjzFGHoOo7WiYjMGBHqw2gcJgJ-XPyWknB48XP3VN3h7uX7dPye7l8Xl7u0sgY2VIMMcqqxh0bSMrkG3H4v1QSZWXkIGSXc4aSKuiSHMus7or6lYpDsjiegk5y9Ykn3PBWe8dduLg9Cjdl-BMHJ2JXszOxNGZmJ1F7PoXBnr-Jziph__gmxnG-NiHRic8aDSASrvoSSir_w74BtLCj7k
CitedBy_id crossref_primary_10_1016_j_autcon_2025_106368
crossref_primary_10_1016_j_tust_2025_106878
crossref_primary_10_1016_j_tust_2025_106966
crossref_primary_10_1016_j_tust_2025_106605
crossref_primary_10_1109_TITS_2025_3542500
crossref_primary_10_1016_j_jobe_2024_110311
crossref_primary_10_1016_j_aei_2025_103383
crossref_primary_10_1016_j_aei_2024_102929
crossref_primary_10_1016_j_tust_2024_105832
crossref_primary_10_1049_sil2_6624103
crossref_primary_10_1016_j_measurement_2025_117434
crossref_primary_10_3390_rs17010133
crossref_primary_10_1016_j_tust_2025_106630
crossref_primary_10_1016_j_autcon_2025_106210
crossref_primary_10_1016_j_autcon_2025_106234
crossref_primary_10_1007_s43503_025_00054_w
crossref_primary_10_1016_j_enbuild_2025_115955
crossref_primary_10_1016_j_asoc_2024_111622
crossref_primary_10_1111_mice_70067
crossref_primary_10_1016_j_scs_2025_106414
Cites_doi 10.1016/j.aei.2021.101501
10.1016/j.autcon.2022.104187
10.1016/j.aei.2022.101608
10.1016/j.patrec.2020.03.021
10.1016/j.autcon.2022.104412
10.1016/j.cor.2022.106116
10.1016/j.autcon.2021.103860
10.1016/j.ress.2019.106567
10.1016/j.autcon.2019.04.005
10.1016/j.autcon.2022.104613
10.3390/s19194188
10.1111/cgf.13804
10.3390/rs12061005
10.1016/j.autcon.2022.104293
10.1016/j.autcon.2021.103847
10.1016/j.autcon.2022.104345
10.1111/mice.12440
10.1016/j.autcon.2023.104915
10.1145/3326362
10.1111/mice.12731
10.1016/j.tust.2022.104509
10.1016/j.autcon.2021.103995
10.1061/(ASCE)CP.1943-5487.0000929
10.1109/TVCG.2020.3027069
10.1007/s11831-019-09320-4
10.1016/j.tust.2022.104472
10.1016/j.autcon.2018.11.028
10.1007/s41095-021-0229-5
10.1111/mice.12881
10.1016/j.neucom.2019.12.118
10.1016/j.aei.2020.101206
10.1016/j.autcon.2022.104667
10.1016/j.autcon.2019.102911
10.1016/j.patcog.2020.107446
10.1016/j.autcon.2021.103934
10.1109/TPAMI.2016.2644615
10.1016/j.autcon.2021.103675
10.1016/j.autcon.2022.104456
10.1109/TPAMI.2020.3005434
10.1016/j.autcon.2021.103610
10.1016/j.autcon.2022.104668
ContentType Journal Article
Copyright 2023 Elsevier B.V.
Copyright_xml – notice: 2023 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.autcon.2023.105131
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Economics
Engineering
EISSN 1872-7891
ExternalDocumentID 10_1016_j_autcon_2023_105131
S0926580523003916
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
23N
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
ABFNM
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACIWK
ACNNM
ACRLP
ADBBV
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
APLSM
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LY7
M41
MO0
N9A
NEJ
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RIG
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SET
SEW
SPC
SPCBC
SSB
SSD
SST
SSZ
T5K
WUQ
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABJNI
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-e4e7370cfb9a7cabf0092c7ad46c3cdaf409c2755241a38f58bdd1ce09a76c403
ISICitedReferencesCount 24
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001105973700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0926-5805
IngestDate Sat Nov 29 07:13:22 EST 2025
Tue Nov 18 22:42:20 EST 2025
Fri Feb 23 02:35:46 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Tunnel point cloud
3D dual attention module
Semantic segmentation
Encoder-decoder
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-e4e7370cfb9a7cabf0092c7ad46c3cdaf409c2755241a38f58bdd1ce09a76c403
ParticipantIDs crossref_primary_10_1016_j_autcon_2023_105131
crossref_citationtrail_10_1016_j_autcon_2023_105131
elsevier_sciencedirect_doi_10_1016_j_autcon_2023_105131
PublicationCentury 2000
PublicationDate December 2023
2023-12-00
PublicationDateYYYYMMDD 2023-12-01
PublicationDate_xml – month: 12
  year: 2023
  text: December 2023
PublicationDecade 2020
PublicationTitle Automation in construction
PublicationYear 2023
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Wang, Huang, Hou, Zhang, Shan (bb0120) 2019
Zhou, Fang, Gao, Huang, Zhong, Shang (bb0130) 2020; 133
Horache, Deschaud, Goulette (bb0260) 2021
Xu, Tong, Stilla (bb0140) 2021; 126
Hassani, Haley (bb0195) 2019
Wang, Yu, Huang, Neumann (bb0090) 2018
Dung, Anh (bb0235) 2019; 99
Y. Wang, Y. Sun, Z. Liu, S.E. Sarma, M.M. Bronstein, J.M. Solomon, Dynamic graph Cnn for learning on point clouds, ACM Trans. Graph. 38 (2019) 146, doi:10.1145/3326362.
Zhang, Zuo, Xu, Wu, Zhu, Zhang, Wang, Tian (bb0295) 2022; 144
Komarichev, Zhong, Hua (bb0105) 2019
Liu, Ni, Li, Yang, Tian (bb0185) 2019
Chew, Ji, Zhang (bb0210) 2022; 133
Guo, Wang, Hu, Liu, Liu, Bennamoun (bb0065) 2021; 43
Ye, Sung (bb0220) 2019
Feng, Zhang, Lin, Gilani, Mian (bb0125) 2020; 107
Qi, Yi, Su, Guibas (bb0085) 2017
Pham, Nguyen, Hua, Roig, Yeung (bb0110) 2019
Zhou, Zhao, Adolfsson, Su, Gao, Duckett, Sun (bb0270) 2021
Hu, Li, Wang, Zhang, Wei, Yang (bb0005) 2023; 151
Mirzaei, Arashpour, Asadi, Masoumi, Bai, Behnood (bb0070) 2022; 51
Zhang, Lu, Qin, He (bb0255) 2021; 27
Zhang, Xie, Li, Zhou, Wang, Shahrour (bb0040) 2022; 139
Xue, Jia, Cai, Shadabfar, Huang (bb0050) 2022; 37
Zhao, Zhang, Xue, Zhou, Huang (bb0045) 2021; 132
Cheng, Qiu, Duan (bb0055) 2019; 106
Argyroudis, Mitoulis, Winter, Kaynia (bb0025) 2019; 191
Graham, Engelcke, Van Der Maaten (bb0165) 2018
Mirzaei, Arashpour, Asadi, Masoumi, Bai, Behnood (bb0145) 2022; 51
Zhang, Ji, Wang, Zhang (bib304) 2022; 142
Guo, Cai, Liu, Mu, Martin, Hu (bb0275) 2021; 7
Xu, Li, Xie, Wu, Wang (bb0030) 2021; 178
Li, Bu, Sun, Wu, Di, Chen (bb0100) 2018
Zhou, Ji, Zhang, Xue (bib303) 2023; 146
Ali, Cha (bb0285) 2022; 141
Fu, Liu, Tian, Li, Bao, Fang, Lu (bb0300) 2019
Lin, Broere, Cui (bb0010) 2022; 125
Chu, Wang, Deng (bb0280) 2022; 37
Chen, Zhu, Papandreou, Schroff, Adam (bb0215) 2018
Han, Chen, Li, Liu, Leng, Ahmed, Zhang (bb0015) 2022; 140
Badrinarayanan, Kendall, Cipolla (bb0230) 2017; 39
Ji, Chew, Xue, Zhang (bib302) 2022; 137
Liu, Cao, Wang, Wang (bb0245) 2019; 104
Zhang, Ji, Zhang, Xu, Zhou (bb0150) 2023; 152
Zhou, Wang, Mao, Gong, Liu (bb0115) 2019; 39
Dang, Wang, Li, Park, Oh, Nguyen, Moon (bb0035) 2022; 124
Meng, Gao, Lai, Manocha (bb0175) 2019
Hu, Hao, Wei, Li (bb0290) 2022; 52
Wang, Suo, Ma, Pokrovsky, Urtasun (bb0155) 2018
Qi, Su, Kaichun, Guibas (bb0080) 2017
Liu, Sun, Li, Hu, Wang (bb0135) 2019; 19
Bang, Park, Kim, Kim (bb0240) 2019; 34
Duan, Qiu, Cheng, Zheng, Lu (bb0060) 2021; 130
Wang, Tan, Mei (bb0075) 2020; 27
Ji, Zhou, Zhang, Tiong, Xue (bib301) 2023; 146
Lee, Park, Ryu (bb0205) 2021; 130
Li, Xie, Gong, Yu, Xu, Sun, Wang (bb0020) 2021; 47
Fotsing, Menadjou, Bobda (bb0160) 2021; 125
Chen, Feng, McCullough, Prasad, McAlinden, Soibelman (bb0250) 2020; 34
Du, Li, Yang, Horng (bb0225) 2020; 388
Zhang, Hao, Wang, de Silva, Fu (bb0190) 2019
Ye, Li, Huang, Du, Zhang (bb0095) 2018
Zhou, Tuzel (bb0170) 2018
Yang, Zhang, Ni, Li, Liu, Zhou, Tian (bb0265) 2019
Pierdicca, Paolanti, Matrone, Martini, Morbidoni, Malinverni, Frontoni, Lingua (bb0200) 2020; 12
10.1016/j.autcon.2023.105131_bb0180
Liu (10.1016/j.autcon.2023.105131_bb0245) 2019; 104
Liu (10.1016/j.autcon.2023.105131_bb0185) 2019
Wang (10.1016/j.autcon.2023.105131_bb0075) 2020; 27
Chen (10.1016/j.autcon.2023.105131_bb0215) 2018
Zhang (10.1016/j.autcon.2023.105131_bib304) 2022; 142
Hassani (10.1016/j.autcon.2023.105131_bb0195) 2019
Komarichev (10.1016/j.autcon.2023.105131_bb0105) 2019
Mirzaei (10.1016/j.autcon.2023.105131_bb0070) 2022; 51
Xue (10.1016/j.autcon.2023.105131_bb0050) 2022; 37
Bang (10.1016/j.autcon.2023.105131_bb0240) 2019; 34
Lin (10.1016/j.autcon.2023.105131_bb0010) 2022; 125
Zhao (10.1016/j.autcon.2023.105131_bb0045) 2021; 132
Li (10.1016/j.autcon.2023.105131_bb0020) 2021; 47
Cheng (10.1016/j.autcon.2023.105131_bb0055) 2019; 106
Pierdicca (10.1016/j.autcon.2023.105131_bb0200) 2020; 12
Zhou (10.1016/j.autcon.2023.105131_bb0270) 2021
Duan (10.1016/j.autcon.2023.105131_bb0060) 2021; 130
Lee (10.1016/j.autcon.2023.105131_bb0205) 2021; 130
Ali (10.1016/j.autcon.2023.105131_bb0285) 2022; 141
Guo (10.1016/j.autcon.2023.105131_bb0275) 2021; 7
Qi (10.1016/j.autcon.2023.105131_bb0085) 2017
Wang (10.1016/j.autcon.2023.105131_bb0090) 2018
Dang (10.1016/j.autcon.2023.105131_bb0035) 2022; 124
Dung (10.1016/j.autcon.2023.105131_bb0235) 2019; 99
Wang (10.1016/j.autcon.2023.105131_bb0155) 2018
Horache (10.1016/j.autcon.2023.105131_bb0260) 2021
Meng (10.1016/j.autcon.2023.105131_bb0175) 2019
Zhou (10.1016/j.autcon.2023.105131_bb0130) 2020; 133
Yang (10.1016/j.autcon.2023.105131_bb0265) 2019
Wang (10.1016/j.autcon.2023.105131_bb0120) 2019
Graham (10.1016/j.autcon.2023.105131_bb0165) 2018
Ji (10.1016/j.autcon.2023.105131_bib302) 2022; 137
Li (10.1016/j.autcon.2023.105131_bb0100) 2018
Du (10.1016/j.autcon.2023.105131_bb0225) 2020; 388
Han (10.1016/j.autcon.2023.105131_bb0015) 2022; 140
Mirzaei (10.1016/j.autcon.2023.105131_bb0145) 2022; 51
Chu (10.1016/j.autcon.2023.105131_bb0280) 2022; 37
Hu (10.1016/j.autcon.2023.105131_bb0005) 2023; 151
Chew (10.1016/j.autcon.2023.105131_bb0210) 2022; 133
Zhou (10.1016/j.autcon.2023.105131_bb0115) 2019; 39
Qi (10.1016/j.autcon.2023.105131_bb0080) 2017
Xu (10.1016/j.autcon.2023.105131_bb0140) 2021; 126
Zhou (10.1016/j.autcon.2023.105131_bib303) 2023; 146
Ye (10.1016/j.autcon.2023.105131_bb0220) 2019
Hu (10.1016/j.autcon.2023.105131_bb0290) 2022; 52
Argyroudis (10.1016/j.autcon.2023.105131_bb0025) 2019; 191
Zhang (10.1016/j.autcon.2023.105131_bb0255) 2021; 27
Ji (10.1016/j.autcon.2023.105131_bib301) 2023; 146
Zhang (10.1016/j.autcon.2023.105131_bb0295) 2022; 144
Ye (10.1016/j.autcon.2023.105131_bb0095) 2018
Fu (10.1016/j.autcon.2023.105131_bb0300) 2019
Zhang (10.1016/j.autcon.2023.105131_bb0040) 2022; 139
Guo (10.1016/j.autcon.2023.105131_bb0065) 2021; 43
Feng (10.1016/j.autcon.2023.105131_bb0125) 2020; 107
Fotsing (10.1016/j.autcon.2023.105131_bb0160) 2021; 125
Badrinarayanan (10.1016/j.autcon.2023.105131_bb0230) 2017; 39
Chen (10.1016/j.autcon.2023.105131_bb0250) 2020; 34
Zhou (10.1016/j.autcon.2023.105131_bb0170) 2018
Liu (10.1016/j.autcon.2023.105131_bb0135) 2019; 19
Xu (10.1016/j.autcon.2023.105131_bb0030) 2021; 178
Zhang (10.1016/j.autcon.2023.105131_bb0190) 2019
Pham (10.1016/j.autcon.2023.105131_bb0110) 2019
Zhang (10.1016/j.autcon.2023.105131_bb0150) 2023; 152
References_xml – volume: 388
  start-page: 269
  year: 2020
  end-page: 279
  ident: bb0225
  article-title: Multivariate time series forecasting via attention-based encoder–decoder framework
  publication-title: Neurocomputing.
– start-page: 10288
  year: 2019
  end-page: 10297
  ident: bb0120
  article-title: Graph attention convolution for point cloud semantic segmentation
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– start-page: 8499
  year: 2019
  end-page: 8507
  ident: bb0175
  article-title: VV-net: Voxel VAE net with group convolutions for point cloud segmentation
  publication-title: Proc. IEEE Int. Conf. Comput. Vis.
– volume: 12
  start-page: 1005
  year: 2020
  ident: bb0200
  article-title: Point cloud semantic segmentation using a deep learning framework for cultural heritage
  publication-title: Remote Sens.
– volume: 137
  start-page: 104187
  year: 2022
  ident: bib302
  article-title: An encoder-decoder deep learning method for multi-class object segmentation from 3D tunnel point clouds
  publication-title: Autom. Constr.
– start-page: 1
  year: 2021
  end-page: 7
  ident: bb0270
  article-title: NDT-transformer: large-scale 3D point cloud localisation using the normal distribution transform representation
  publication-title: ArXiv.
– start-page: 4490
  year: 2018
  end-page: 4499
  ident: bb0170
  article-title: VoxelNet: end-to-end learning for point cloud based 3D object detection
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– volume: 151
  year: 2023
  ident: bb0005
  article-title: Robust metro train scheduling integrated with skip-stop pattern and passenger flow control strategy under uncertain passenger demands
  publication-title: Comput. Oper. Res.
– volume: 133
  start-page: 327
  year: 2020
  end-page: 333
  ident: bb0130
  article-title: Feature fusion network based on attention mechanism for 3D semantic segmentation of point clouds
  publication-title: Pattern Recogn. Lett.
– start-page: 7545
  year: 2019
  end-page: 7554
  ident: bb0185
  article-title: Dynamic points agglomeration for hierarchical point sets learning
  publication-title: Proc. IEEE Int. Conf. Comput. Vis.
– start-page: 7064
  year: 2019
  end-page: 7073
  ident: bb0220
  article-title: Understanding geometry of encoder-decoder CNNs
  publication-title: Proc. 36th Int. Conf. Mach. Learn. PMLR
– volume: 146
  start-page: 104667
  year: 2023
  ident: bib303
  article-title: Attention-enhanced sampling point cloud network (ASPCNet) for efficient 3D tunnel semantic segmentation
  publication-title: Autom. Constr.
– start-page: 1351
  year: 2021
  end-page: 1361
  ident: bb0260
  article-title: 3D point cloud registration with multi-scale architecture and unsupervised transfer learning
  publication-title: Proc. 2021 Int. Conf. 3D Vis.
– volume: 39
  start-page: 2481
  year: 2017
  end-page: 2495
  ident: bb0230
  article-title: SegNet: a deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 47
  year: 2021
  ident: bb0020
  article-title: Automatic defect detection of metro tunnel surfaces using a vision-based inspection system
  publication-title: Adv. Eng. Inform.
– volume: 107
  year: 2020
  ident: bb0125
  article-title: Point attention network for semantic segmentation of 3D point clouds
  publication-title: Pattern Recogn.
– volume: 130
  year: 2021
  ident: bb0205
  article-title: Semantic segmentation of bridge components based on hierarchical point cloud model
  publication-title: Autom. Constr.
– volume: 133
  year: 2022
  ident: bb0210
  article-title: Large-scale 3D point-cloud semantic segmentation of urban and rural scenes using data volume decomposition coupled with pipeline parallelism
  publication-title: Autom. Constr.
– start-page: 1
  year: 2017
  end-page: 14
  ident: bb0085
  article-title: PointNet++: deep hierarchical feature learning on point sets in a metric space
  publication-title: ArXiv.
– start-page: 801
  year: 2018
  end-page: 818
  ident: bb0215
  article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation
  publication-title: Proc. Eur. Conf. Comput. Vis. (ECCV)
– start-page: 7413
  year: 2019
  end-page: 7422
  ident: bb0105
  article-title: A-CNN: Annularly convolutional neural networks on point clouds
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– start-page: 1
  year: 2019
  end-page: 8
  ident: bb0190
  article-title: Linked dynamic graph CNN: learning on point cloud via linking hierarchical features
  publication-title: ArXiv.
– volume: 106
  year: 2019
  ident: bb0055
  article-title: Automatic creation of as-is building information model from single-track railway tunnel point clouds
  publication-title: Autom. Constr.
– volume: 191
  year: 2019
  ident: bb0025
  article-title: Fragility of transport assets exposed to multiple hazards: state-of-the-art review toward infrastructural resilience
  publication-title: Reliab. Eng. Syst. Saf.
– volume: 124
  year: 2022
  ident: bb0035
  article-title: Automatic tunnel lining crack evaluation and measurement using deep learning
  publication-title: Tunn. Undergr. Sp. Technol.
– volume: 104
  start-page: 129
  year: 2019
  end-page: 139
  ident: bb0245
  article-title: Computer vision-based concrete crack detection using U-net fully convolutional networks
  publication-title: Autom. Constr.
– volume: 43
  start-page: 4338
  year: 2021
  end-page: 4364
  ident: bb0065
  article-title: Deep learning for 3D point clouds: a survey
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 7
  start-page: 187
  year: 2021
  end-page: 199
  ident: bb0275
  article-title: PCT: point cloud transformer
  publication-title: Comput. Vis. Media.
– volume: 125
  year: 2021
  ident: bb0160
  article-title: Iterative closest point for accurate plane detection in unorganized point clouds
  publication-title: Autom. Constr.
– volume: 178
  year: 2021
  ident: bb0030
  article-title: Automatic defect detection and segmentation of tunnel surface using modified mask R-CNN
  publication-title: Meas. J. Int. Meas. Confed.
– volume: 140
  year: 2022
  ident: bb0015
  article-title: Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels
  publication-title: Autom. Constr.
– volume: 27
  start-page: 479
  year: 2020
  end-page: 499
  ident: bb0075
  article-title: Computational methods of acquisition and processing of 3D point cloud data for construction applications
  publication-title: Arch. Comput. Methods Eng.
– volume: 142
  start-page: 104456
  year: 2022
  ident: bib304
  article-title: UnrollingNet: an attention-based deep learning approach for the segmentation of large-scale point clouds of tunnels
  publication-title: Autom. Constr.
– volume: 37
  start-page: 386
  year: 2022
  end-page: 402
  ident: bb0050
  article-title: An optimization strategy to improve the deep learning-based recognition model of leakage in shield tunnels
  publication-title: Comput. Civ. Infrastruct. Eng.
– volume: 51
  year: 2022
  ident: bb0070
  article-title: 3D point cloud data processing with machine learning for construction and infrastructure applications: a comprehensive review
  publication-title: Adv. Eng. Inform.
– start-page: 652
  year: 2017
  end-page: 660
  ident: bb0080
  article-title: PointNet: Deep learning on point sets for 3D classification and segmentation
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recogn.
– start-page: 2569
  year: 2018
  end-page: 2578
  ident: bb0090
  article-title: SGPN: Similarity group proposal network for 3D point cloud instance segmentation
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– volume: 99
  start-page: 52
  year: 2019
  end-page: 58
  ident: bb0235
  article-title: Autonomous concrete crack detection using deep fully convolutional neural network
  publication-title: Autom. Constr.
– start-page: 403
  year: 2018
  end-page: 417
  ident: bb0095
  article-title: 3D recurrent neural networks with context fusion for point cloud semantic segmentation
  publication-title: Proc. Eur. Conf. Comput. Vis.
– volume: 126
  year: 2021
  ident: bb0140
  article-title: Voxel-based representation of 3D point clouds: methods, applications, and its potential use in the construction industry
  publication-title: Autom. Constr.
– volume: 52
  year: 2022
  ident: bb0290
  article-title: An efficient solder joint defects method for 3D point clouds with double-flow region attention network
  publication-title: Adv. Eng. Inform.
– volume: 39
  start-page: 309
  year: 2019
  end-page: 321
  ident: bb0115
  article-title: SiamesePointNet: a siamese point network architecture for learning 3D shape descriptor
  publication-title: Comput. Graph Forum.
– volume: 125
  year: 2022
  ident: bb0010
  article-title: Metro systems and urban development: impacts and implications
  publication-title: Tunn. Undergr. Sp. Technol.
– start-page: 8159
  year: 2019
  end-page: 8170
  ident: bb0195
  article-title: Unsupervised multi-task feature learning on point clouds
  publication-title: Proc. IEEE Int. Conf. Comput. Vis.
– volume: 34
  start-page: 713
  year: 2019
  end-page: 727
  ident: bb0240
  article-title: Encoder–decoder network for pixel-level road crack detection in black-box images
  publication-title: Comput. Civ. Infrastruct. Eng.
– reference: Y. Wang, Y. Sun, Z. Liu, S.E. Sarma, M.M. Bronstein, J.M. Solomon, Dynamic graph Cnn for learning on point clouds, ACM Trans. Graph. 38 (2019) 146, doi:10.1145/3326362.
– volume: 37
  start-page: 1914
  year: 2022
  end-page: 1931
  ident: bb0280
  article-title: Tiny-crack-net: a multiscale feature fusion network with attention mechanisms for segmentation of tiny cracks
  publication-title: Comput. Civ. Infrastruct. Eng.
– volume: 146
  start-page: 104668
  year: 2023
  ident: bib301
  article-title: Semi-supervised learning-based point cloud network for segmentation of 3D tunnel scenes
  publication-title: Autom. Constr.
– volume: 130
  year: 2021
  ident: bb0060
  article-title: Reconstruction of shield tunnel lining using point cloud
  publication-title: Autom. Constr.
– volume: 141
  year: 2022
  ident: bb0285
  article-title: Attention-based generative adversarial network with internal damage segmentation using thermography
  publication-title: Autom. Constr.
– volume: 139
  year: 2022
  ident: bb0040
  article-title: Subway tunnel damage detection based on in-service train dynamic response, variational mode decomposition, convolutional neural networks and long short-term memory
  publication-title: Autom. Constr.
– start-page: 3141
  year: 2019
  end-page: 3149
  ident: bb0300
  article-title: Dual attention network for scene segmentation
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– volume: 27
  start-page: 2015
  year: 2021
  end-page: 2027
  ident: bb0255
  article-title: Pointfilter: point cloud filtering via encoder-decoder modeling
  publication-title: IEEE Trans. Vis. Comput. Graph.
– volume: 34
  start-page: 04020048
  year: 2020
  ident: bb0250
  article-title: 3D photogrammetry point cloud segmentation using a model ensembling framework
  publication-title: J. Comput. Civ. Eng.
– volume: 152
  year: 2023
  ident: bb0150
  article-title: Deep learning for large-scale point cloud segmentation in tunnels considering causal inference
  publication-title: Autom. Constr.
– start-page: 9224
  year: 2018
  end-page: 9232
  ident: bb0165
  article-title: 3D semantic segmentation with submanifold sparse convolutional networks
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– start-page: 828
  year: 2018
  end-page: 838
  ident: bb0100
  article-title: PointCNN: Convolution on X-transformed points
  publication-title: Conf. Neural Inf. Process. Syst.
– volume: 132
  year: 2021
  ident: bb0045
  article-title: A deep learning-based approach for refined crack evaluation from shield tunnel lining images
  publication-title: Autom. Constr.
– start-page: 3318
  year: 2019
  end-page: 3327
  ident: bb0265
  article-title: Modeling point clouds with self-attention and gumbel subset sampling
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– volume: 51
  year: 2022
  ident: bb0145
  article-title: 3D point cloud data processing with machine learning for construction and infrastructure applications: a comprehensive review
  publication-title: Adv. Eng. Inform.
– volume: 144
  year: 2022
  ident: bb0295
  article-title: Road damage detection using UAV images based on multi-level attention mechanism
  publication-title: Autom. Constr.
– start-page: 2589
  year: 2018
  end-page: 2597
  ident: bb0155
  article-title: Deep parametric continuous convolutional neural networks
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– volume: 19
  start-page: 4188
  year: 2019
  ident: bb0135
  article-title: Deep learning on point clouds and its application: a survey
  publication-title: Sensors (Switzerland).
– start-page: 8819
  year: 2019
  end-page: 8828
  ident: bb0110
  article-title: JSIS3D: Joint semantic-instance segmentation of 3D point clouds with multi-task pointwise networks and multi-value conditional random fields
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
– volume: 51
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0070
  article-title: 3D point cloud data processing with machine learning for construction and infrastructure applications: a comprehensive review
  publication-title: Adv. Eng. Inform.
  doi: 10.1016/j.aei.2021.101501
– volume: 137
  start-page: 104187
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bib302
  article-title: An encoder-decoder deep learning method for multi-class object segmentation from 3D tunnel point clouds
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104187
– start-page: 801
  year: 2018
  ident: 10.1016/j.autcon.2023.105131_bb0215
  article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation
– volume: 52
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0290
  article-title: An efficient solder joint defects method for 3D point clouds with double-flow region attention network
  publication-title: Adv. Eng. Inform.
  doi: 10.1016/j.aei.2022.101608
– volume: 133
  start-page: 327
  year: 2020
  ident: 10.1016/j.autcon.2023.105131_bb0130
  article-title: Feature fusion network based on attention mechanism for 3D semantic segmentation of point clouds
  publication-title: Pattern Recogn. Lett.
  doi: 10.1016/j.patrec.2020.03.021
– volume: 141
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0285
  article-title: Attention-based generative adversarial network with internal damage segmentation using thermography
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104412
– start-page: 1
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0270
  article-title: NDT-transformer: large-scale 3D point cloud localisation using the normal distribution transform representation
  publication-title: ArXiv.
– volume: 151
  year: 2023
  ident: 10.1016/j.autcon.2023.105131_bb0005
  article-title: Robust metro train scheduling integrated with skip-stop pattern and passenger flow control strategy under uncertain passenger demands
  publication-title: Comput. Oper. Res.
  doi: 10.1016/j.cor.2022.106116
– volume: 130
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0060
  article-title: Reconstruction of shield tunnel lining using point cloud
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2021.103860
– volume: 191
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0025
  article-title: Fragility of transport assets exposed to multiple hazards: state-of-the-art review toward infrastructural resilience
  publication-title: Reliab. Eng. Syst. Saf.
  doi: 10.1016/j.ress.2019.106567
– volume: 104
  start-page: 129
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0245
  article-title: Computer vision-based concrete crack detection using U-net fully convolutional networks
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2019.04.005
– volume: 144
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0295
  article-title: Road damage detection using UAV images based on multi-level attention mechanism
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104613
– volume: 19
  start-page: 4188
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0135
  article-title: Deep learning on point clouds and its application: a survey
  publication-title: Sensors (Switzerland).
  doi: 10.3390/s19194188
– volume: 39
  start-page: 309
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0115
  article-title: SiamesePointNet: a siamese point network architecture for learning 3D shape descriptor
  publication-title: Comput. Graph Forum.
  doi: 10.1111/cgf.13804
– volume: 12
  start-page: 1005
  year: 2020
  ident: 10.1016/j.autcon.2023.105131_bb0200
  article-title: Point cloud semantic segmentation using a deep learning framework for cultural heritage
  publication-title: Remote Sens.
  doi: 10.3390/rs12061005
– start-page: 9224
  year: 2018
  ident: 10.1016/j.autcon.2023.105131_bb0165
  article-title: 3D semantic segmentation with submanifold sparse convolutional networks
– volume: 139
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0040
  article-title: Subway tunnel damage detection based on in-service train dynamic response, variational mode decomposition, convolutional neural networks and long short-term memory
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104293
– start-page: 1
  year: 2017
  ident: 10.1016/j.autcon.2023.105131_bb0085
  article-title: PointNet++: deep hierarchical feature learning on point sets in a metric space
  publication-title: ArXiv.
– start-page: 7545
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0185
  article-title: Dynamic points agglomeration for hierarchical point sets learning
– start-page: 8159
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0195
  article-title: Unsupervised multi-task feature learning on point clouds
– volume: 130
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0205
  article-title: Semantic segmentation of bridge components based on hierarchical point cloud model
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2021.103847
– volume: 140
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0015
  article-title: Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104345
– volume: 34
  start-page: 713
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0240
  article-title: Encoder–decoder network for pixel-level road crack detection in black-box images
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12440
– volume: 152
  year: 2023
  ident: 10.1016/j.autcon.2023.105131_bb0150
  article-title: Deep learning for large-scale point cloud segmentation in tunnels considering causal inference
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2023.104915
– ident: 10.1016/j.autcon.2023.105131_bb0180
  doi: 10.1145/3326362
– volume: 37
  start-page: 386
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0050
  article-title: An optimization strategy to improve the deep learning-based recognition model of leakage in shield tunnels
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12731
– start-page: 10288
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0120
  article-title: Graph attention convolution for point cloud semantic segmentation
– volume: 125
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0010
  article-title: Metro systems and urban development: impacts and implications
  publication-title: Tunn. Undergr. Sp. Technol.
  doi: 10.1016/j.tust.2022.104509
– start-page: 2589
  year: 2018
  ident: 10.1016/j.autcon.2023.105131_bb0155
  article-title: Deep parametric continuous convolutional neural networks
– start-page: 8499
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0175
  article-title: VV-net: Voxel VAE net with group convolutions for point cloud segmentation
– volume: 133
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0210
  article-title: Large-scale 3D point-cloud semantic segmentation of urban and rural scenes using data volume decomposition coupled with pipeline parallelism
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2021.103995
– volume: 51
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0145
  article-title: 3D point cloud data processing with machine learning for construction and infrastructure applications: a comprehensive review
  publication-title: Adv. Eng. Inform.
  doi: 10.1016/j.aei.2021.101501
– volume: 34
  start-page: 04020048
  year: 2020
  ident: 10.1016/j.autcon.2023.105131_bb0250
  article-title: 3D photogrammetry point cloud segmentation using a model ensembling framework
  publication-title: J. Comput. Civ. Eng.
  doi: 10.1061/(ASCE)CP.1943-5487.0000929
– start-page: 1
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0190
  article-title: Linked dynamic graph CNN: learning on point cloud via linking hierarchical features
  publication-title: ArXiv.
– volume: 27
  start-page: 2015
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0255
  article-title: Pointfilter: point cloud filtering via encoder-decoder modeling
  publication-title: IEEE Trans. Vis. Comput. Graph.
  doi: 10.1109/TVCG.2020.3027069
– volume: 27
  start-page: 479
  year: 2020
  ident: 10.1016/j.autcon.2023.105131_bb0075
  article-title: Computational methods of acquisition and processing of 3D point cloud data for construction applications
  publication-title: Arch. Comput. Methods Eng.
  doi: 10.1007/s11831-019-09320-4
– volume: 124
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0035
  article-title: Automatic tunnel lining crack evaluation and measurement using deep learning
  publication-title: Tunn. Undergr. Sp. Technol.
  doi: 10.1016/j.tust.2022.104472
– volume: 99
  start-page: 52
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0235
  article-title: Autonomous concrete crack detection using deep fully convolutional neural network
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2018.11.028
– start-page: 7413
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0105
  article-title: A-CNN: Annularly convolutional neural networks on point clouds
– start-page: 3141
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0300
  article-title: Dual attention network for scene segmentation
– volume: 7
  start-page: 187
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0275
  article-title: PCT: point cloud transformer
  publication-title: Comput. Vis. Media.
  doi: 10.1007/s41095-021-0229-5
– volume: 37
  start-page: 1914
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bb0280
  article-title: Tiny-crack-net: a multiscale feature fusion network with attention mechanisms for segmentation of tiny cracks
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12881
– volume: 388
  start-page: 269
  year: 2020
  ident: 10.1016/j.autcon.2023.105131_bb0225
  article-title: Multivariate time series forecasting via attention-based encoder–decoder framework
  publication-title: Neurocomputing.
  doi: 10.1016/j.neucom.2019.12.118
– start-page: 2569
  year: 2018
  ident: 10.1016/j.autcon.2023.105131_bb0090
  article-title: SGPN: Similarity group proposal network for 3D point cloud instance segmentation
– start-page: 828
  year: 2018
  ident: 10.1016/j.autcon.2023.105131_bb0100
  article-title: PointCNN: Convolution on X-transformed points
  publication-title: Conf. Neural Inf. Process. Syst.
– volume: 47
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0020
  article-title: Automatic defect detection of metro tunnel surfaces using a vision-based inspection system
  publication-title: Adv. Eng. Inform.
  doi: 10.1016/j.aei.2020.101206
– start-page: 1351
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0260
  article-title: 3D point cloud registration with multi-scale architecture and unsupervised transfer learning
– volume: 178
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0030
  article-title: Automatic defect detection and segmentation of tunnel surface using modified mask R-CNN
  publication-title: Meas. J. Int. Meas. Confed.
– start-page: 3318
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0265
  article-title: Modeling point clouds with self-attention and gumbel subset sampling
– volume: 146
  start-page: 104667
  year: 2023
  ident: 10.1016/j.autcon.2023.105131_bib303
  article-title: Attention-enhanced sampling point cloud network (ASPCNet) for efficient 3D tunnel semantic segmentation
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104667
– volume: 106
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0055
  article-title: Automatic creation of as-is building information model from single-track railway tunnel point clouds
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2019.102911
– volume: 107
  year: 2020
  ident: 10.1016/j.autcon.2023.105131_bb0125
  article-title: Point attention network for semantic segmentation of 3D point clouds
  publication-title: Pattern Recogn.
  doi: 10.1016/j.patcog.2020.107446
– volume: 132
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0045
  article-title: A deep learning-based approach for refined crack evaluation from shield tunnel lining images
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2021.103934
– volume: 39
  start-page: 2481
  year: 2017
  ident: 10.1016/j.autcon.2023.105131_bb0230
  article-title: SegNet: a deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2644615
– start-page: 403
  year: 2018
  ident: 10.1016/j.autcon.2023.105131_bb0095
  article-title: 3D recurrent neural networks with context fusion for point cloud semantic segmentation
– start-page: 8819
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0110
  article-title: JSIS3D: Joint semantic-instance segmentation of 3D point clouds with multi-task pointwise networks and multi-value conditional random fields
– volume: 126
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0140
  article-title: Voxel-based representation of 3D point clouds: methods, applications, and its potential use in the construction industry
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2021.103675
– volume: 142
  start-page: 104456
  year: 2022
  ident: 10.1016/j.autcon.2023.105131_bib304
  article-title: UnrollingNet: an attention-based deep learning approach for the segmentation of large-scale point clouds of tunnels
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104456
– volume: 43
  start-page: 4338
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0065
  article-title: Deep learning for 3D point clouds: a survey
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.3005434
– volume: 125
  year: 2021
  ident: 10.1016/j.autcon.2023.105131_bb0160
  article-title: Iterative closest point for accurate plane detection in unorganized point clouds
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2021.103610
– start-page: 652
  year: 2017
  ident: 10.1016/j.autcon.2023.105131_bb0080
  article-title: PointNet: Deep learning on point sets for 3D classification and segmentation
– volume: 146
  start-page: 104668
  year: 2023
  ident: 10.1016/j.autcon.2023.105131_bib301
  article-title: Semi-supervised learning-based point cloud network for segmentation of 3D tunnel scenes
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2022.104668
– start-page: 4490
  year: 2018
  ident: 10.1016/j.autcon.2023.105131_bb0170
  article-title: VoxelNet: end-to-end learning for point cloud based 3D object detection
– start-page: 7064
  year: 2019
  ident: 10.1016/j.autcon.2023.105131_bb0220
  article-title: Understanding geometry of encoder-decoder CNNs
SSID ssj0007069
Score 2.4952345
Snippet Aiming to automatically segment multi-class objects on the tunnel point cloud, a deep learning network named dual attention-based point cloud network (DAPCNet)...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 105131
SubjectTerms 3D dual attention module
Deep learning
Encoder-decoder
Semantic segmentation
Tunnel point cloud
Title Dual attention-based deep learning network for multi-class object semantic segmentation of tunnel point clouds
URI https://dx.doi.org/10.1016/j.autcon.2023.105131
Volume 156
WOSCitedRecordID wos001105973700001&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-7891
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007069
  issn: 0926-5805
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWLRLlgKCAKC_5wC2ylM3L2WMFRQWhCoki5RY5trNK2U0WNlv12n_OTMZJQxfxkrhYURTHq5kv9nj2m8-MvdJhFJjURkKqMhaRUb5QpQqFtRqWF2WklHTYhDw9TbNs_nEyueprYS6Wsq7Ty8v5-r-6Gu6Bs7F09i_cPbwUbsA1OB1acDu0f-T4N1gQgqqZHY9R4DJlPGPtuj8hYuHVxP3uKIYdo1BoDKK9psCsjLexK7B3peFisXK1SV1U2W6RFeOtm6puPb1stlQlPKjYbtuGKiG9jt1-LU478HQqIlF-UW7BHKesP1Qr1Qx4osTsSVMvvlZD_2zb5V-zSsGc7V7hUhZBeIP-sVtLQwnJIBFx6tN_3Jam41RC_J_SeV7DfE1K5DtzP6UhzpH5g6kEHBhPMZ65VeZHVe1POByOBlswFMlPbrG9QMbzdMr2jt4dZ--H5Vz6CQk2up_X1192JMHdsX4e34xilrP77J7bbPAjAskDNrH1AbvT16JvDtjdkRzlQ1YjdPgN6HCEDu-hwx10OECHj6DDCTq8hw4fQ4c3JSfo8A46nKDziH1-e3z2-kS48ziEho1lK2xkZSh9XRZzJbUqShTs0lKZKNGhNqqM_LkGI8YQFaowLeO0MGamrQ-PJzryw8dsWje1fcJ4rFRhZRHbmQ0iaAownZwFMkFBQGnSQxb2Vsy1E6vHM1OWec9KPM_J9jnaPifbHzIx9FqTWMtvnpe9g3IXcFIgmQOmftnz6T_3fMb2rz-J52wKH6J9wW7ri7bafHvpwPcdiDSsXA
linkProvider Elsevier
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=Dual+attention-based+deep+learning+network+for+multi-class+object+semantic+segmentation+of+tunnel+point+clouds&rft.jtitle=Automation+in+construction&rft.au=Ji%2C+Ankang&rft.au=Zhang%2C+Limao&rft.au=Fan%2C+Hongqin&rft.au=Xue%2C+Xiaolong&rft.date=2023-12-01&rft.pub=Elsevier+B.V&rft.issn=0926-5805&rft.eissn=1872-7891&rft.volume=156&rft_id=info:doi/10.1016%2Fj.autcon.2023.105131&rft.externalDocID=S0926580523003916
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0926-5805&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0926-5805&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0926-5805&client=summon