Impact of loss functions on semantic segmentation in far‐field monitoring
Although previous research laid the foundation for vision‐based monitoring systems using convolutional neural networks (CNNs), too little attention has been paid to the challenges associated with data imbalance and varying object sizes in far‐field monitoring. To fill the knowledge gap, this paper i...
Saved in:
| Published in: | Computer-aided civil and infrastructure engineering Vol. 38; no. 3; pp. 372 - 390 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Hoboken
Wiley Subscription Services, Inc
01.02.2023
|
| Subjects: | |
| ISSN: | 1093-9687, 1467-8667 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Although previous research laid the foundation for vision‐based monitoring systems using convolutional neural networks (CNNs), too little attention has been paid to the challenges associated with data imbalance and varying object sizes in far‐field monitoring. To fill the knowledge gap, this paper investigates various loss functions to design a customized loss function to address the challenges. Scaffold installation operations recorded by camcorders were selected as the subject of analysis in a far‐field surveillance setting. It was confirmed that the data imbalance between the workers, hardhats, harnesses, straps, and hooks caused poor performances especially for small size objects. This problem was mitigated by employing a region‐based loss and Focal loss terms in the loss function of segmentation models. The findings illustrate the importance of the loss function design in improving performance of CNN models for far‐field construction site monitoring. |
|---|---|
| AbstractList | Although previous research laid the foundation for vision‐based monitoring systems using convolutional neural networks (CNNs), too little attention has been paid to the challenges associated with data imbalance and varying object sizes in far‐field monitoring. To fill the knowledge gap, this paper investigates various loss functions to design a customized loss function to address the challenges. Scaffold installation operations recorded by camcorders were selected as the subject of analysis in a far‐field surveillance setting. It was confirmed that the data imbalance between the workers, hardhats, harnesses, straps, and hooks caused poor performances especially for small size objects. This problem was mitigated by employing a region‐based loss and Focal loss terms in the loss function of segmentation models. The findings illustrate the importance of the loss function design in improving performance of CNN models for far‐field construction site monitoring. |
| Author | Chern, Wei‐Chih Nguyen, Tam V. Kim, Hongjo Asari, Vijayan K. |
| Author_xml | – sequence: 1 givenname: Wei‐Chih surname: Chern fullname: Chern, Wei‐Chih organization: University of Dayton – sequence: 2 givenname: Tam V. surname: Nguyen fullname: Nguyen, Tam V. organization: University of Dayton – sequence: 3 givenname: Vijayan K. surname: Asari fullname: Asari, Vijayan K. organization: University of Dayton – sequence: 4 givenname: Hongjo surname: Kim fullname: Kim, Hongjo email: hongjo@yonsei.ac.kr organization: Yonsei University |
| BookMark | eNp9kMFKAzEQhoNUsK1efIKAN2FrssluNkcptRYrXvQcstmkpOwmNdkivfkIPqNPYup6EnEuM8N8_wzzT8DIeacBuMRohlPcdFbpGc4rkp-AMaYly6qyZKNUI04yXlbsDExi3KIUlJIxeFh1O6l66A1sfYzQ7J3qrXcRegej7qTrrUrFptOul8cJtA4aGT7fP4zVbQM772zvg3Wbc3BqZBv1xU-egpe7xfP8Pls_LVfz23WmCMJ5VnDDG6QqSRpaUyqVklzr1OeKpYZVBUKFajjXBtW44LSpOeHY1KqoKJeKTMHVsHcX_Otex15s_T64dFLkjBGGUTIgUWigVEiPBW2EssMHfZC2FRiJo2XiaJn4tixJrn9JdsF2Mhz-hvEAv9lWH_4hxeNqvhg0X787gI0 |
| CitedBy_id | crossref_primary_10_1111_mice_13343 crossref_primary_10_1016_j_autcon_2024_105277 crossref_primary_10_1111_mice_13396 crossref_primary_10_1111_mice_13153 crossref_primary_10_1109_TGRS_2024_3516501 crossref_primary_10_3390_electronics14112244 crossref_primary_10_1016_j_autcon_2024_105604 crossref_primary_10_1016_j_autcon_2025_106099 crossref_primary_10_1111_mice_13422 crossref_primary_10_1111_mice_13443 |
| Cites_doi | 10.1007/s11263-014-0733-5 10.1111/mice.12458 10.1016/j.autcon.2020.103085 10.1111/mice.12701 10.1016/j.compmedimag.2022.102112 10.1061/(ASCE)CP.1943-5487.0000923 10.1016/j.autcon.2021.103721 10.1088/0964-1726/24/6/065034 10.5220/0010211600700079 10.1109/ICAIIC51459.2021.9415217 10.1016/j.autcon.2021.103817 10.1111/exsy.12647 10.1016/j.compbiomed.2021.104815 10.14359/51689560 10.1007/s00170-022-08721-3 10.1111/mice.12632 10.1111/mice.12667 10.1049/iet-ipr.2019.1527 10.1016/j.autcon.2020.103356 10.1016/j.neunet.2018.07.011 10.1016/j.autcon.2019.02.006 10.1111/mice.12741 10.1109/TKDE.2009.191 10.1061/(ASCE)CO.1943-7862.0001570 10.1016/j.autcon.2021.103670 10.1109/TKDE.2008.239 10.1109/ICCV.2017.324 10.1007/978-3-030-00931-1_70 10.1016/j.autcon.2020.103198 10.1007/978-3-319-24574-4_28 10.1109/IJCNN.2016.7727770 10.1016/j.autcon.2021.103620 10.48550/arXiv.2108.03235 10.1016/j.autcon.2021.103606 10.1016/j.compmedimag.2019.02.001 10.1061/(ASCE)CO.1943-7862.0001047 10.1016/j.patrec.2008.04.005 10.1109/3DV.2016.79 10.1016/j.jobe.2021.102913 10.1016/j.autcon.2021.103785 10.1111/mice.12419 10.1109/VCIP.2017.8305148 10.1109/MIPR49039.2020.00066 10.1002/mp.13300 10.3233/ICA-210649 10.1016/j.asoc.2017.05.029 10.1016/j.autcon.2021.103572 10.1111/mice.12505 10.1016/j.autcon.2018.04.002 10.1016/j.aei.2020.101100 10.1002/tal.1312 10.1016/j.autcon.2019.103013 10.1109/CVPR.2017.106 10.1016/j.engstruct.2018.10.065 |
| ContentType | Journal Article |
| Copyright | 2022 . 2023 Computer‐Aided Civil and Infrastructure Engineering. |
| Copyright_xml | – notice: 2022 . – notice: 2023 Computer‐Aided Civil and Infrastructure Engineering. |
| DBID | AAYXX CITATION 7SC 8FD FR3 JQ2 KR7 L7M L~C L~D |
| DOI | 10.1111/mice.12832 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Civil Engineering Abstracts CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Computer Science |
| EISSN | 1467-8667 |
| EndPage | 390 |
| ExternalDocumentID | 10_1111_mice_12832 MICE12832 |
| Genre | article |
| GrantInformation_xml | – fundername: Korea Agency for Infrastructure Technology Advancement under the Ministry of Land – fundername: Infrastructure and Transport, and managed by the Korea Expressway Corporation |
| GroupedDBID | ..I .3N .4S .DC .GA 05W 0R~ 10A 1OB 1OC 29F 31~ 33P 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 5GY 5HH 5LA 5VS 66C 6P2 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A03 AAESR AAEVG AAHHS AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDBF ABEML ABFSI ABJNI ACAHQ ACBWZ ACCFJ ACCZN ACGFS ACPOU ACRPL ACSCC ACUHS ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN ADZOD AEEZP AEIGN AEIMD AENEX AEQDE AEUQT AEUYR AFBPY AFEBI AFFPM AFGKR AFPWT AHBTC AHEFC AI. AITYG AIURR AIWBW AJBDE AJXKR ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ARCSS ASPBG ATUGU AUFTA AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BY8 CAG COF CS3 CWDTD D-E D-F DCZOG DPXWK DR2 DRFUL DRSTM DU5 E.L EAD EAP EBS EDO EJD EMK EST ESX F00 F01 F04 FEDTE G-S G.N GODZA H.T H.X HF~ HGLYW HVGLF HZI HZ~ I-F IHE IX1 J0M K48 LATKE LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MK4 MK~ MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 NF~ O66 O9- OIG P2P P2W P2X P4D PALCI Q.N Q11 QB0 R.K RJQFR RX1 SAMSI SUPJJ TN5 TUS UB1 VH1 W8V W99 WBKPD WIH WIK WLBEL WOHZO WQJ WRC WXSBR WYISQ XG1 ZZTAW ~IA ~WT AAMMB AAYXX ADMLS AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY AIQQE CITATION O8X 7SC 8FD FR3 JQ2 KR7 L7M L~C L~D |
| ID | FETCH-LOGICAL-c3012-59f9d0c8a3d4b44acca9eec8a2c7acc785005cd99ef0b1594db9391fbc5849ac3 |
| IEDL.DBID | DRFUL |
| ISICitedReferencesCount | 16 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000762839800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1093-9687 |
| IngestDate | Sun Nov 09 05:45:09 EST 2025 Sat Nov 29 05:42:09 EST 2025 Tue Nov 18 21:43:07 EST 2025 Wed Jan 22 16:18:59 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3012-59f9d0c8a3d4b44acca9eec8a2c7acc785005cd99ef0b1594db9391fbc5849ac3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| PQID | 2773710283 |
| PQPubID | 2045171 |
| PageCount | 19 |
| ParticipantIDs | proquest_journals_2773710283 crossref_citationtrail_10_1111_mice_12832 crossref_primary_10_1111_mice_12832 wiley_primary_10_1111_mice_12832_MICE12832 |
| PublicationCentury | 2000 |
| PublicationDate | February 2023 2023-02-00 20230201 |
| PublicationDateYYYYMMDD | 2023-02-01 |
| PublicationDate_xml | – month: 02 year: 2023 text: February 2023 |
| PublicationDecade | 2020 |
| PublicationPlace | Hoboken |
| PublicationPlace_xml | – name: Hoboken |
| PublicationTitle | Computer-aided civil and infrastructure engineering |
| PublicationYear | 2023 |
| Publisher | Wiley Subscription Services, Inc |
| Publisher_xml | – name: Wiley Subscription Services, Inc |
| References | 1901; 37 2021; 124 2019; 97 2021; 126 2020; 120 2021; 125 2021; 128 2021; 28 2021; 127 2021; 129 2020; 14 2008; 30 2017; 114 2016; 142 2018; 46 2021; 36 2010; 22 2021; 37 2020; 45 1948 2018; 144 2021; 43 2009; 21 2019; 73 2021; 2 2018; 106 2017; 26 2011 2019; 34 2009 2019; 102 2020; 37 2020; 35 2020; 34 2018; 25 2015; 24 2017; 58 2021 2020 2020; 110 2015; 111 2020; 115 2018; 92 2019 2018 2017 2016 2020; 112 2015 2014 2019; 178 e_1_2_8_24_1 e_1_2_8_47_1 e_1_2_8_26_1 e_1_2_8_49_1 e_1_2_8_5_1 e_1_2_8_7_1 e_1_2_8_9_1 e_1_2_8_20_1 e_1_2_8_43_1 e_1_2_8_66_1 e_1_2_8_22_1 e_1_2_8_45_1 e_1_2_8_64_1 Li B. (e_1_2_8_28_1) 2018 e_1_2_8_62_1 e_1_2_8_41_1 e_1_2_8_60_1 e_1_2_8_17_1 e_1_2_8_19_1 e_1_2_8_13_1 e_1_2_8_36_1 e_1_2_8_59_1 e_1_2_8_15_1 Tan M. (e_1_2_8_57_1) 2019; 97 e_1_2_8_55_1 e_1_2_8_11_1 e_1_2_8_34_1 e_1_2_8_53_1 e_1_2_8_51_1 e_1_2_8_30_1 Kisantal M. (e_1_2_8_27_1) 2019 Lin T. (e_1_2_8_32_1) 2014 e_1_2_8_29_1 Pang J. (e_1_2_8_48_1) 2019 Amezquita‐Sanchez J. P. (e_1_2_8_3_1) 2018; 25 e_1_2_8_25_1 Olga R. (e_1_2_8_46_1) 2014 e_1_2_8_2_1 e_1_2_8_4_1 e_1_2_8_6_1 e_1_2_8_8_1 e_1_2_8_21_1 e_1_2_8_42_1 e_1_2_8_67_1 Wu Y. (e_1_2_8_63_1) 2021; 2 e_1_2_8_44_1 e_1_2_8_65_1 e_1_2_8_40_1 e_1_2_8_61_1 e_1_2_8_18_1 e_1_2_8_39_1 e_1_2_8_14_1 Jaccard P. (e_1_2_8_23_1) 1901; 37 e_1_2_8_35_1 e_1_2_8_16_1 e_1_2_8_37_1 e_1_2_8_58_1 Martins G. B. (e_1_2_8_38_1) 2020; 37 e_1_2_8_10_1 e_1_2_8_31_1 e_1_2_8_56_1 e_1_2_8_12_1 e_1_2_8_33_1 e_1_2_8_54_1 e_1_2_8_52_1 e_1_2_8_50_1 |
| References_xml | – volume: 28 start-page: 221 issue: 3 year: 2021 end-page: 235 article-title: An ensemble deep learning method with optimized weights for drone‐based water rescue and surveillance publication-title: Integrated Computer‐Aided Engineering – year: 2011 article-title: SMOTE: Synthetic minority over‐sampling technique publication-title: CoRR – year: 2009 – volume: 34 start-page: 333 issue: 4 year: 2019 end-page: 351 article-title: Capturing and understanding workers activities in far‐field surveillance videos with deep action recognition and Bayesian nonparametric learning publication-title: Computer‐Aided Civil and Infrastructure Engineering – volume: 102 start-page: 135 year: 2019 end-page: 147 article-title: Vision‐based nonintrusive context documentation for earthmoving productivity simulation publication-title: Automation in Construction – volume: 126 year: 2021 article-title: Integrated worker detection and tracking for the safe operation of construction machinery publication-title: Automation in Construction – volume: 111 start-page: 98 issue: 1 year: 2015 article-title: The Pascal visual object classes challenge: A retrospective publication-title: International Journal of Computer Vision – volume: 128 year: 2021 article-title: A deep learning approach for fast detection and classification of concrete damage publication-title: Automation in Construction – volume: 45 year: 2020 article-title: Real‐time smart video surveillance to manage safety: A case study of a transport mega‐project publication-title: Advanced Engineering Informatics – year: 2021 – volume: 178 start-page: 603 year: 2019 end-page: 615 article-title: Recurrent neural network model with Bayesian training and mutual information for response prediction of large buildings publication-title: Engineering Structures – volume: 14 start-page: 2682 year: 2020 end-page: 2689 article-title: Denseunet: Densely connected unet for electron microscopy image segmentation publication-title: IET Image Processing – volume: 21 start-page: 1263 issue: 9 year: 2009 end-page: 1284 article-title: Learning from imbalanced data publication-title: IEEE Transactions on Knowledge and Data Engineering, Knowledge and Data Engineering – volume: 36 start-page: 302 issue: 3 year: 2021 end-page: 317 article-title: Semi‐supervised learning based on convolutional neural network and uncertainty filter for façade defects classification publication-title: Computer‐Aided Civil and Infrastructure Engineering – volume: 58 start-page: 576 year: 2017 end-page: 585 article-title: Evolutionary learning based sustainable strain sensing model for structural health monitoring of high‐rise buildings publication-title: Applied Soft Computing Journal – year: 2019 article-title: Libra R‐CNN: Towards balanced learning for object detection publication-title: Computer Vision and Pattern Recognition (CVPR) – year: 2018 – volume: 34 start-page: 755 issue: 9 year: 2019 end-page: 773 article-title: Deep leaf‐bootstrapping generative adversarial network for structural image data augmentation publication-title: Computer‐Aided Civil and Infrastructure Engineering – start-page: 70 year: 2021 end-page: 79 – volume: 36 start-page: 620 issue: 5 year: 2021 end-page: 637 article-title: Pixel‐level multicategory detection of visible seismic damage of reinforced concrete components publication-title: Computer‐Aided Civil and Infrastructure Engineering – volume: 114 start-page: 237 issue: 2 year: 2017 end-page: 244 article-title: Supervised deep restricted Boltzmann machine for estimation of concrete publication-title: ACI Materials Journal – volume: 115 year: 2020 article-title: Image augmentation to improve construction resource detection using generative adversarial networks, cut‐and‐paste, and image transformation techniques publication-title: Automation in Construction – volume: 144 issue: 12 year: 2018 article-title: Novel machine‐learning model for estimating construction costs considering economic variables and indexes publication-title: Journal of Construction Engineering and Management – start-page: 1 year: 2017 end-page: 4 – start-page: 181 year: 2021 end-page: 186 – volume: 73 start-page: 60 year: 2019 end-page: 72 article-title: 3D convolutional neural networks for tumor segmentation using long‐range 2D context publication-title: Computerized Medical Imaging and Graphics – volume: 37 start-page: 1 issue: 6 year: 2020 end-page: 21 article-title: Deep learning techniques for recommender systems based on collaborative filtering publication-title: Expert Systems: International Journal of Knowledge Engineering and Neural Networks – year: 2014 article-title: Imagenet large scale visual recognition challenge publication-title: arXiv – volume: 25 start-page: 2913 issue: 6 year: 2018 end-page: 2925 article-title: Wireless smart sensors for monitoring the health condition of civil infrastructure publication-title: Scientia Iranica – year: 2018 article-title: Gradient harmonized single‐stage detector publication-title: arXiv – volume: 26 issue: 3 year: 2017 article-title: New method for modal identification of super high‐rise building structures using discretized synchrosqueezed wavelet and Hilbert transforms publication-title: Structural Design of Tall & Special Buildings – volume: 124 year: 2021 article-title: Temporal image analytics for abnormal construction activity identification publication-title: Automation in Construction – year: 2021 article-title: Simple copy‐paste is a strong data augmentation method for instance segmentation publication-title: Computer Vision and Pattern Recognition (CVPR) – year: 2015 – volume: 142 issue: 2 year: 2016 article-title: A novel machine learning model for estimation of sale prices of real estate units publication-title: Journal of Construction Engineering and Management – volume: 35 start-page: 465 issue: 5 year: 2020 end-page: 482 article-title: Vision‐based automated bridge component recognition with high‐level scene consistency publication-title: Computer‐Aided Civil and Infrastructure Engineering – volume: 34 issue: 6 year: 2020 article-title: Video‐based motion trajectory forecasting method for proactive construction safety monitoring systems publication-title: Journal of Computing in Civil Engineering – volume: 127 year: 2021 article-title: A vision‐based method for automatic tracking of construction machines at nighttime based on deep learning illumination enhancement publication-title: Automation in Construction – volume: 110 year: 2020 article-title: Computer vision applications in construction safety assurance publication-title: Automation in Construction – volume: 22 start-page: 1345 issue: 10 year: 2010 end-page: 1359 article-title: A survey on transfer learning publication-title: IEEE Transactions on Knowledge and Data Engineering – volume: 125 year: 2021 article-title: Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning publication-title: Automation in Construction – volume: 46 start-page: 576 issue: 2 year: 2018 end-page: 589 article-title: Anatomynet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy publication-title: Medical Physics – volume: 36 start-page: 1094 year: 2021 end-page: 1113 article-title: Balanced semisupervised generative adversarial network for damage assessment from low‐data imbalanced‐class regime publication-title: Computer‐Aided Civil and Infrastructure Engineering – year: 1948 – volume: 37 start-page: 547 year: 1901 end-page: 579 article-title: Étude comparative de la distribution florale dans une portion des alpes et des jura publication-title: Bulletin del la Société Vaudoise des Sciences Naturelles – year: 2016 – volume: 92 start-page: 188 year: 2018 end-page: 198 article-title: Analyzing context and productivity of tunnel earthmoving processes using imaging and simulation publication-title: Automation in Construction – volume: 24 issue: 6 year: 2015 article-title: Synchrosqueezed wavelet transform‐fractality model for locating, detecting, and quantifying damage in smart highrise building structures publication-title: Smart Materials and Structures – start-page: 612 year: 2018 end-page: 619 – volume: 129 year: 2021 article-title: Vision‐based method of automatically detecting construction video highlights by integrating machine tracking and CNN feature extraction publication-title: Automation in Construction – volume: 21 start-page: 1263 issue: 9 year: 2009 end-page: 1284 article-title: Learning from imbalanced data publication-title: IEEE Transactions on Knowledge and Data Engineering – volume: 97 start-page: 6105 year: 2019 end-page: 6114 article-title: Efficientnet: Rethinking model scaling for convolutional neural networks publication-title: International Conference on Machine Learning – volume: 37 start-page: 145 issue: 2 year: 2021 end-page: 162 article-title: Deep semantic segmentation for visual understanding on construction sites publication-title: Computer‐Aided Civil and Infrastructure Engineering – volume: 106 start-page: 249 year: 2018 end-page: 259 article-title: A systematic study of the class imbalance problem in convolutional neural networks publication-title: Neural Networks – year: 2014 article-title: Microsoft COCO: Common objects in context publication-title: CoRR – volume: 125 year: 2021 article-title: A vision‐based approach for automatic progress tracking of floor paneling in offsite construction facilities publication-title: Automation in Construction – year: 2020 – volume: 30 start-page: 88 issue: 2 year: 2008 end-page: 97 article-title: Semantic object classes in video: A high‐definition ground truth database publication-title: Pattern Recognition Letters – year: 2019 article-title: Augmentation for small object detection publication-title: ArXiv – year: 2017 article-title: Feature pyramid networks for object detection publication-title: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 2 start-page: 227 year: 2021 end-page: 244 article-title: Hybrid deep learning architecture for rail surface segmentation and surface defect detection publication-title: Computer‐Aided Civil and Infrastructure Engineering – volume: 43 year: 2021 article-title: Automated crack segmentation in close‐range building facade inspection images using deep learning techniques publication-title: Journal of Building Engineering – volume: 120 year: 2020 article-title: Human‐object interaction recognition for automatic construction site safety inspection publication-title: Automation in Construction – volume: 112 year: 2020 article-title: Deep learning for site safety: Real‐time detection of personal protective equipment publication-title: Automation in Construction – ident: e_1_2_8_13_1 doi: 10.1007/s11263-014-0733-5 – ident: e_1_2_8_15_1 doi: 10.1111/mice.12458 – ident: e_1_2_8_44_1 doi: 10.1016/j.autcon.2020.103085 – ident: e_1_2_8_61_1 doi: 10.1111/mice.12701 – ident: e_1_2_8_20_1 doi: 10.1016/j.compmedimag.2022.102112 – year: 2019 ident: e_1_2_8_48_1 article-title: Libra R‐CNN: Towards balanced learning for object detection publication-title: Computer Vision and Pattern Recognition (CVPR) – ident: e_1_2_8_58_1 doi: 10.1061/(ASCE)CP.1943-5487.0000923 – ident: e_1_2_8_64_1 doi: 10.1016/j.autcon.2021.103721 – ident: e_1_2_8_2_1 doi: 10.1088/0964-1726/24/6/065034 – ident: e_1_2_8_54_1 doi: 10.5220/0010211600700079 – ident: e_1_2_8_30_1 doi: 10.1109/ICAIIC51459.2021.9415217 – volume: 25 start-page: 2913 issue: 6 year: 2018 ident: e_1_2_8_3_1 article-title: Wireless smart sensors for monitoring the health condition of civil infrastructure publication-title: Scientia Iranica – ident: e_1_2_8_65_1 doi: 10.1016/j.autcon.2021.103817 – volume: 37 start-page: 1 issue: 6 year: 2020 ident: e_1_2_8_38_1 article-title: Deep learning techniques for recommender systems based on collaborative filtering publication-title: Expert Systems: International Journal of Knowledge Engineering and Neural Networks doi: 10.1111/exsy.12647 – ident: e_1_2_8_66_1 doi: 10.1016/j.compbiomed.2021.104815 – ident: e_1_2_8_52_1 doi: 10.14359/51689560 – ident: e_1_2_8_18_1 doi: 10.1007/s00170-022-08721-3 – ident: e_1_2_8_19_1 doi: 10.1111/mice.12632 – ident: e_1_2_8_39_1 doi: 10.1111/mice.12667 – ident: e_1_2_8_8_1 doi: 10.1049/iet-ipr.2019.1527 – ident: e_1_2_8_59_1 doi: 10.1016/j.autcon.2020.103356 – ident: e_1_2_8_7_1 doi: 10.1016/j.neunet.2018.07.011 – ident: e_1_2_8_26_1 doi: 10.1016/j.autcon.2019.02.006 – ident: e_1_2_8_16_1 doi: 10.1111/mice.12741 – ident: e_1_2_8_47_1 doi: 10.1109/TKDE.2009.191 – ident: e_1_2_8_51_1 doi: 10.1061/(ASCE)CO.1943-7862.0001570 – ident: e_1_2_8_55_1 doi: 10.1016/j.autcon.2021.103670 – ident: e_1_2_8_21_1 doi: 10.1109/TKDE.2008.239 – ident: e_1_2_8_33_1 doi: 10.1109/ICCV.2017.324 – ident: e_1_2_8_62_1 doi: 10.1007/978-3-030-00931-1_70 – ident: e_1_2_8_42_1 – ident: e_1_2_8_4_1 doi: 10.1016/j.autcon.2020.103198 – ident: e_1_2_8_53_1 doi: 10.1007/978-3-319-24574-4_28 – volume: 2 start-page: 227 year: 2021 ident: e_1_2_8_63_1 article-title: Hybrid deep learning architecture for rail surface segmentation and surface defect detection publication-title: Computer‐Aided Civil and Infrastructure Engineering – ident: e_1_2_8_60_1 doi: 10.1109/IJCNN.2016.7727770 – ident: e_1_2_8_37_1 doi: 10.1016/j.autcon.2021.103620 – volume: 37 start-page: 547 year: 1901 ident: e_1_2_8_23_1 article-title: Étude comparative de la distribution florale dans une portion des alpes et des jura publication-title: Bulletin del la Société Vaudoise des Sciences Naturelles – ident: e_1_2_8_5_1 doi: 10.48550/arXiv.2108.03235 – ident: e_1_2_8_56_1 – ident: e_1_2_8_12_1 doi: 10.1016/j.autcon.2021.103606 – ident: e_1_2_8_41_1 doi: 10.1016/j.compmedimag.2019.02.001 – ident: e_1_2_8_50_1 doi: 10.1061/(ASCE)CO.1943-7862.0001047 – ident: e_1_2_8_6_1 doi: 10.1016/j.patrec.2008.04.005 – ident: e_1_2_8_40_1 doi: 10.1109/3DV.2016.79 – ident: e_1_2_8_11_1 doi: 10.1016/j.jobe.2021.102913 – ident: e_1_2_8_24_1 doi: 10.1016/j.autcon.2021.103785 – ident: e_1_2_8_36_1 doi: 10.1111/mice.12419 – year: 2014 ident: e_1_2_8_46_1 article-title: Imagenet large scale visual recognition challenge publication-title: arXiv – ident: e_1_2_8_9_1 doi: 10.1109/VCIP.2017.8305148 – ident: e_1_2_8_10_1 doi: 10.1109/MIPR49039.2020.00066 – ident: e_1_2_8_67_1 doi: 10.1002/mp.13300 – ident: e_1_2_8_17_1 doi: 10.3233/ICA-210649 – volume: 97 start-page: 6105 year: 2019 ident: e_1_2_8_57_1 article-title: Efficientnet: Rethinking model scaling for convolutional neural networks publication-title: International Conference on Machine Learning – ident: e_1_2_8_45_1 doi: 10.1016/j.asoc.2017.05.029 – ident: e_1_2_8_34_1 doi: 10.1016/j.autcon.2021.103572 – year: 2014 ident: e_1_2_8_32_1 article-title: Microsoft COCO: Common objects in context publication-title: CoRR – ident: e_1_2_8_43_1 doi: 10.1111/mice.12505 – ident: e_1_2_8_25_1 doi: 10.1016/j.autcon.2018.04.002 – year: 2018 ident: e_1_2_8_28_1 article-title: Gradient harmonized single‐stage detector publication-title: arXiv – ident: e_1_2_8_22_1 doi: 10.1109/TKDE.2008.239 – ident: e_1_2_8_35_1 doi: 10.1016/j.aei.2020.101100 – ident: e_1_2_8_29_1 doi: 10.1002/tal.1312 – ident: e_1_2_8_14_1 doi: 10.1016/j.autcon.2019.103013 – year: 2019 ident: e_1_2_8_27_1 article-title: Augmentation for small object detection publication-title: ArXiv – ident: e_1_2_8_31_1 doi: 10.1109/CVPR.2017.106 – ident: e_1_2_8_49_1 doi: 10.1016/j.engstruct.2018.10.065 |
| SSID | ssj0000443 |
| Score | 2.440182 |
| Snippet | Although previous research laid the foundation for vision‐based monitoring systems using convolutional neural networks (CNNs), too little attention has been... |
| SourceID | proquest crossref wiley |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 372 |
| SubjectTerms | Artificial neural networks Construction sites Harnesses Hooks Monitoring Semantic segmentation Straps |
| Title | Impact of loss functions on semantic segmentation in far‐field monitoring |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fmice.12832 https://www.proquest.com/docview/2773710283 |
| Volume | 38 |
| WOSCitedRecordID | wos000762839800001&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: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1467-8667 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000443 issn: 1093-9687 databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NSsQwEB509aAH119cXSWgF4XKtk1tA15EXRRFRBS8lfzKwm5XturZR_AZfRInaequIIJ4S0IaQma-mS9lMgOw25HUGLR5ATpPEdBMiEAoFQYijA4TykOV8I4rNpFeX2cPD-xmCo7qtzBVfoivH24WGc5eW4BzUU6A3FZrPwhtpZ1pmIlQcZMGzJzedu-vxpaY-gB7FgfsMEt9elIbyTP--rtDGrPMSa7qnE23-b9tLsKCJ5nkuNKKJZjSxTI0PeEkHs4lDtU1HeqxZZifSFC4ApcX7hElGRrSx80T6wWdopJhQUo9QLH0JDYeB_4JU0F6BTF89PH27mLjyMDZDLvaKtx3z-5OzgNffiGQiHq8ojLDVEdmPFZUUMpR1kxr7EcyxU6aJYhgqRjTpiOQFVElWMxCIySSGsZlvAaNYljodSAR1egtRawijt7QaMazRMeJZMpEzFDegr1aBrn0ucltiYx-Xt9R7DHm7hhbsPM196nKyPHjrHYtytyjssyjNI0rRtWCfSe0X1bIEQZnrrXxl8mbMGcr0leB3W1oPI9e9BbMytfnXjna9hr6CW9E678 |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEB58gXqwPrE-A3pRWOnuZt3NUdSiWIuIgrclTynYrbTq2Z_gb_SXOMlm2woiiLdkyYaQmW_mS5jMAOw3JDUGbV6AzlMENBMiEEqFgQij44TyUCW84YpNpO129vDAbnxsjn0LU-aHGF64WWQ4e20Bbi-kx1Buy7UfhbbUziRMU9QjVPDps9vmfWtkiqmPsGdxwI6z1OcntaE8o7-_e6QRzRwnq87bNGv_XOciLHiaSU5KvViCCV0sQ81TTuIBPcBPVVWH6tsyzI-lKFyBq0v3jJL0DHnC1RPrB52qkl5BBrqLgulIbDx2_SOmgnQKYnj_8_3DRceRrrMadrZVuG-e351eBL4AQyAR93hIZYaphsx4rKiglKO0mdbYj2SKnTRLEMNSMaZNQyAvokqwmIVGSKQ1jMt4DaaKXqHXgURUo78UsYo4-kOjGc8SHSeSKRMxQ3kdDioh5NJnJ7dFMp7y6pRitzF321iHveHY5zInx4-jtipZ5h6XgzxK07jkVHU4dFL7ZYYcgXDuWht_GbwLsxd31628ddm-2oQ5W5--DPPegqmX_qvehhn59tIZ9He8un4BiVDvrw |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEB60iujBt1ifAb0orHR3s93NUdSiKEVEwduSpxTarbTq2Z_gb_SXOMlm2woiiLckzIaQyTczWSbzARw2JDUGbV6AzlMENBMiEEqFgQijZkJ5qBLecGQTabudPT6yW5-bY9_ClPUhRj_cLDKcvbYA18_KTKDc0rWfhJZqZxpmqGWRqcHM-V3r4WZsiqnPsGdxwJpZ6uuT2lSe8dffPdI4zJwMVp23aS39c53LsOjDTHJanosVmNLFKiz5kJN4QA9xqGJ1qMZWYWGiROEaXF-5Z5Skb0gXV0-sH3RHlfQLMtQ9VExHYuOp5x8xFaRTEMMHn-8fLjuO9JzVsLOtw0Pr4v7sMvAEDIFE3OMllRmmGjLjsaKCUo7aZlpjP5IpdtIsQQxLxZg2DYFxEVWCxSw0QmJYw7iMN6BW9Au9CSSiGv2liFXE0R8azXiW6DiRTJmIGcrrcFQpIZe-Orklyejm1S3FbmPutrEOByPZ57Imx49SO5Uuc4_LYR6laVzGVHU4dlr7ZYYcgXDhWlt_Ed6HudvzVn5z1b7ehnlLT19mee9A7WXwqndhVr69dIaDPX9avwAtYe8q |
| 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=Impact+of+loss+functions+on+semantic+segmentation+in+far%E2%80%90field+monitoring&rft.jtitle=Computer-aided+civil+and+infrastructure+engineering&rft.au=Chern%2C+Wei%E2%80%90Chih&rft.au=Nguyen%2C+Tam+V.&rft.au=Asari%2C+Vijayan+K.&rft.au=Kim%2C+Hongjo&rft.date=2023-02-01&rft.issn=1093-9687&rft.eissn=1467-8667&rft.volume=38&rft.issue=3&rft.spage=372&rft.epage=390&rft_id=info:doi/10.1111%2Fmice.12832&rft.externalDBID=n%2Fa&rft.externalDocID=10_1111_mice_12832 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1093-9687&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1093-9687&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1093-9687&client=summon |