DGW‐YOLOv8: A small insulator target detection algorithm based on deformable attention backbone and WIoU loss function

The YOLO series of algorithms have made substantial contributions to the detection of insulator defects in power transmission line operations. However, existing target detection algorithms for the small target detection and low‐quality insulator images encounter difficulties in effectively capturing...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IET image processing Ročník 18; číslo 4; s. 1096 - 1108
Hlavní autoři:	Hu, Deao, Yu, Mei, Wu, Xianyong, Hu, Jingbo, Sheng, Yuyang, Jiang, Yanjing, Huang, Chongjing, Zheng, Yuelin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Wiley 01.03.2024
Témata:	computer vision image recognition insulators object detection
ISSN:	1751-9659, 1751-9667
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The YOLO series of algorithms have made substantial contributions to the detection of insulator defects in power transmission line operations. However, existing target detection algorithms for the small target detection and low‐quality insulator images encounter difficulties in effectively capturing relevant features, resulting in a higher probability of target loss. To identify and classify defects in the operational state of insulators, an improved YOLOv8 target identification algorithm called DGW‐YOLOv8 is proposed in this paper. The deformable attention backbone of the DGW‐YOLOv8 target identification algorithm is designed by adding the deformable ConvNets v2 module and the global attention mechanism. This addition reduces the feature loss caused by the network feature processing, enhances the sensitivity of the algorithm to small‐scale targets, and reduces the impact caused by the different global positions of the targets. Additionally, to address the problem of low quality of captured images, WIoU v3 is used to replace CIoU in the original YOLOv8 target identification algorithm to optimize the loss function, reduce the degrees of freedom, and improve the network robustness. Experimental results demonstrate that the enhanced YOLOv8 algorithm can achieve an improvement of 2.4% and 5.5% in mAP and mAP50‐95, respectively, compared with the original algorithm. An improved YOLOv8 target identification algorithm called DGW‐YOLOv8 is proposed in this paper. The deformable attention backbone of DGW‐YOLOv8 is improved by adding deformable ConvNets v2 module and the global attention mechanism, WIoU v3 is used to replace CIoU in the original YOLOv8 to optimize the loss function. Experimental results demonstrate that the enhanced YOLOv8 algorithm can achieve an improvement of 2.4% and 5.5% in mAP and mAP50‐95.
AbstractList	Abstract The YOLO series of algorithms have made substantial contributions to the detection of insulator defects in power transmission line operations. However, existing target detection algorithms for the small target detection and low‐quality insulator images encounter difficulties in effectively capturing relevant features, resulting in a higher probability of target loss. To identify and classify defects in the operational state of insulators, an improved YOLOv8 target identification algorithm called DGW‐YOLOv8 is proposed in this paper. The deformable attention backbone of the DGW‐YOLOv8 target identification algorithm is designed by adding the deformable ConvNets v2 module and the global attention mechanism. This addition reduces the feature loss caused by the network feature processing, enhances the sensitivity of the algorithm to small‐scale targets, and reduces the impact caused by the different global positions of the targets. Additionally, to address the problem of low quality of captured images, WIoU v3 is used to replace CIoU in the original YOLOv8 target identification algorithm to optimize the loss function, reduce the degrees of freedom, and improve the network robustness. Experimental results demonstrate that the enhanced YOLOv8 algorithm can achieve an improvement of 2.4% and 5.5% in mAP and mAP50‐95, respectively, compared with the original algorithm. The YOLO series of algorithms have made substantial contributions to the detection of insulator defects in power transmission line operations. However, existing target detection algorithms for the small target detection and low‐quality insulator images encounter difficulties in effectively capturing relevant features, resulting in a higher probability of target loss. To identify and classify defects in the operational state of insulators, an improved YOLOv8 target identification algorithm called DGW‐YOLOv8 is proposed in this paper. The deformable attention backbone of the DGW‐YOLOv8 target identification algorithm is designed by adding the deformable ConvNets v2 module and the global attention mechanism. This addition reduces the feature loss caused by the network feature processing, enhances the sensitivity of the algorithm to small‐scale targets, and reduces the impact caused by the different global positions of the targets. Additionally, to address the problem of low quality of captured images, WIoU v3 is used to replace CIoU in the original YOLOv8 target identification algorithm to optimize the loss function, reduce the degrees of freedom, and improve the network robustness. Experimental results demonstrate that the enhanced YOLOv8 algorithm can achieve an improvement of 2.4% and 5.5% in mAP and mAP50‐95, respectively, compared with the original algorithm. The YOLO series of algorithms have made substantial contributions to the detection of insulator defects in power transmission line operations. However, existing target detection algorithms for the small target detection and low‐quality insulator images encounter difficulties in effectively capturing relevant features, resulting in a higher probability of target loss. To identify and classify defects in the operational state of insulators, an improved YOLOv8 target identification algorithm called DGW‐YOLOv8 is proposed in this paper. The deformable attention backbone of the DGW‐YOLOv8 target identification algorithm is designed by adding the deformable ConvNets v2 module and the global attention mechanism. This addition reduces the feature loss caused by the network feature processing, enhances the sensitivity of the algorithm to small‐scale targets, and reduces the impact caused by the different global positions of the targets. Additionally, to address the problem of low quality of captured images, WIoU v3 is used to replace CIoU in the original YOLOv8 target identification algorithm to optimize the loss function, reduce the degrees of freedom, and improve the network robustness. Experimental results demonstrate that the enhanced YOLOv8 algorithm can achieve an improvement of 2.4% and 5.5% in mAP and mAP50‐95, respectively, compared with the original algorithm. An improved YOLOv8 target identification algorithm called DGW‐YOLOv8 is proposed in this paper. The deformable attention backbone of DGW‐YOLOv8 is improved by adding deformable ConvNets v2 module and the global attention mechanism, WIoU v3 is used to replace CIoU in the original YOLOv8 to optimize the loss function. Experimental results demonstrate that the enhanced YOLOv8 algorithm can achieve an improvement of 2.4% and 5.5% in mAP and mAP50‐95.
Author	Sheng, Yuyang Hu, Deao Huang, Chongjing Wu, Xianyong Jiang, Yanjing Zheng, Yuelin Yu, Mei Hu, Jingbo
Author_xml	– sequence: 1 givenname: Deao orcidid: 0009-0007-0242-5116 surname: Hu fullname: Hu, Deao organization: China Three Gorges University – sequence: 2 givenname: Mei surname: Yu fullname: Yu, Mei email: yumei@ctgu.edu.cn organization: China Three Gorges University – sequence: 3 givenname: Xianyong surname: Wu fullname: Wu, Xianyong organization: China Three Gorges University – sequence: 4 givenname: Jingbo surname: Hu fullname: Hu, Jingbo organization: China Three Gorges University – sequence: 5 givenname: Yuyang surname: Sheng fullname: Sheng, Yuyang organization: China Three Gorges University – sequence: 6 givenname: Yanjing surname: Jiang fullname: Jiang, Yanjing organization: China Three Gorges University – sequence: 7 givenname: Chongjing surname: Huang fullname: Huang, Chongjing organization: China Three Gorges University – sequence: 8 givenname: Yuelin surname: Zheng fullname: Zheng, Yuelin organization: China Three Gorges University
BookMark	eNp9UUtOHDEUtBCR-CSbnMBrpAG77f44O8QvI400KApCWVnP9vPExNNGbkPCjiPkjJyEnhlgEaGs3lOpqlSl2iPbfeqRkM-cHXIm1VG4zdUhF4ypLbLL25pPVNO0229_rXbI3jDcMFYr1tW75M_pxfXT498f89n8vvtCj-mwhBhp6Ie7CCVlWiAvsFCHBW0JqacQFymH8nNJDQzo6Ag59CkvwUSkUAr2a54B-8uM6Sj0jl5P0xWNaRiov-vXPh_JBw9xwE8vd59cnZ99P_k6mc0vpifHs4mVXKpJazlH6YQBNKIySrTWCtN5Di0qqBBFLRnjpukEQy_a1glvLHrWOVCec7FPphtfl-BG3-awhPygEwS9BlJeaMgl2IhaYeWYlbLqnJO-YqbjHVNoVCOb1jZu9GIbL5vHKhm9tqHAqk3JEKLmTK9W0KsV9HqFUXLwj-Q1wrtkviH_DhEf_sPU08tv1UbzDO9nnGg
CitedBy_id	crossref_primary_10_1049_ipr2_13321 crossref_primary_10_3390_fire8040138 crossref_primary_10_1109_JSEN_2025_3552848 crossref_primary_10_1007_s11554_024_01557_y crossref_primary_10_1016_j_compbiomed_2024_109630 crossref_primary_10_1049_cdt2_9984821 crossref_primary_10_1016_j_compbiomed_2025_109778 crossref_primary_10_1016_j_measurement_2024_116605 crossref_primary_10_1016_j_mineng_2025_109712 crossref_primary_10_3390_agronomy14122751 crossref_primary_10_1007_s12145_024_01503_3 crossref_primary_10_1049_ipr2_70180 crossref_primary_10_1016_j_procs_2025_05_128 crossref_primary_10_1080_17538947_2025_2537321 crossref_primary_10_3389_fmech_2025_1635741 crossref_primary_10_1007_s12008_025_02342_2 crossref_primary_10_1049_hve2_70080 crossref_primary_10_1088_2631_8695_adb6f3 crossref_primary_10_1109_TIM_2025_3562980 crossref_primary_10_1080_09544828_2025_2506293 crossref_primary_10_1177_14727978241304269 crossref_primary_10_1007_s13369_025_09997_9 crossref_primary_10_1109_TCPMT_2024_3447040 crossref_primary_10_1109_TIM_2025_3568984 crossref_primary_10_3390_en17112535 crossref_primary_10_1016_j_jvcir_2025_104427 crossref_primary_10_1109_ACCESS_2024_3486311 crossref_primary_10_1109_TIM_2025_3606049 crossref_primary_10_3390_drones8080346 crossref_primary_10_1088_1361_6501_adf65d crossref_primary_10_1049_ipr2_13191 crossref_primary_10_3390_rs16162878 crossref_primary_10_1016_j_neucom_2024_127685 crossref_primary_10_1016_j_autcon_2024_105506 crossref_primary_10_3390_agriculture14060856 crossref_primary_10_1007_s11554_025_01627_9 crossref_primary_10_3390_agronomy15030693 crossref_primary_10_3390_s24134045 crossref_primary_10_3390_jmse13040810 crossref_primary_10_3390_app15010327 crossref_primary_10_1007_s11760_025_04214_4 crossref_primary_10_1016_j_neucom_2025_130207
Cites_doi	10.1109/TIM.2020.3031194 10.1109/TIP.2023.3261749 10.1007/s00521-021-06296-w 10.1109/TIE.2017.2716862 10.1109/TCYB.2021.3095305 10.3390/drones7050304 10.1109/CVPR52688.2022.00089 10.1109/TIM.2022.3194909 10.1109/TPAMI.2022.3164083 10.1007/s40684-021-00343-6 10.1016/j.neucom.2021.03.091 10.1016/j.patcog.2022.109214 10.1109/TIM.2022.3219307 10.1109/TNNLS.2021.3120472 10.1109/TGRS.2023.3321307 10.1109/ACCESS.2020.2997466 10.1109/TPWRD.2007.899760 10.1007/978-3-319-46448-0_2 10.3390/app11104647 10.1109/TCSVT.2023.3234993 10.1109/CVPR46437.2021.00841 10.1007/s11042-018-6610-4 10.1109/ICCVW54120.2021.00312 10.1109/ICCV.2017.324 10.1109/TCYB.2021.3131569 10.1109/CVPR.2014.81 10.1109/CVPR.2019.00075 10.3390/machines11020257 10.1609/aaai.v34i07.6999 10.1016/j.measurement.2019.01.072 10.1109/CVPR52729.2023.00721 10.1109/TPWRD.2007.908779 10.1109/TSMC.2018.2871750 10.1016/j.neunet.2023.03.017
ContentType	Journal Article
Copyright	2023 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
Copyright_xml	– notice: 2023 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
DBID	24P AAYXX CITATION DOA
DOI	10.1049/ipr2.13009
DatabaseName	Wiley Online Library Open Access CrossRef DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef
DatabaseTitleList	CrossRef
Database_xml	– sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher – sequence: 2 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences
EISSN	1751-9667
EndPage	1108
ExternalDocumentID	oai_doaj_org_article_9e2d0c4428dd4f20b81809eb96467c6d 10_1049_ipr2_13009 IPR213009
Genre	article
GroupedDBID	.DC 0R~ 1OC 24P 29I 5GY 6IK 8VB AAHHS AAHJG AAJGR ABQXS ACCFJ ACCMX ACESK ACGFS ACIWK ACXQS ADZOD AEEZP AENEX AEQDE AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN AVUZU CS3 DU5 EBS ESX GROUPED_DOAJ HZ~ IAO IFIPE IPLJI ITC JAVBF LAI MCNEO MS~ O9- OCL OK1 P2P QWB RIE RNS ROL RUI ZL0 4.4 8FE 8FG AAMMB AAYXX ABJCF AEFGJ AFFHD AFKRA AGXDD AIDQK AIDYY ARAPS BENPR BGLVJ CCPQU CITATION EJD HCIFZ IDLOA K1G L6V M43 M7S P62 PHGZM PHGZT PQGLB PTHSS S0W WIN
ID	FETCH-LOGICAL-c4149-7c11e4d3baeb32b937cc3b8f1a7e9a2ee354001b6830ef377d3fbcef08da9f113
IEDL.DBID	24P
ISICitedReferencesCount	49
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001124609100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1751-9659
IngestDate	Mon Nov 10 04:35:56 EST 2025 Tue Nov 18 20:52:16 EST 2025 Wed Oct 29 21:26:45 EDT 2025 Wed Jan 22 16:14:17 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	Attribution
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c4149-7c11e4d3baeb32b937cc3b8f1a7e9a2ee354001b6830ef377d3fbcef08da9f113
ORCID	0009-0007-0242-5116
OpenAccessLink	https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fipr2.13009
PageCount	13
ParticipantIDs	doaj_primary_oai_doaj_org_article_9e2d0c4428dd4f20b81809eb96467c6d crossref_citationtrail_10_1049_ipr2_13009 crossref_primary_10_1049_ipr2_13009 wiley_primary_10_1049_ipr2_13009_IPR213009
PublicationCentury	2000
PublicationDate	2024-03-01
PublicationDateYYYYMMDD	2024-03-01
PublicationDate_xml	– month: 03 year: 2024 text: 2024-03-01 day: 01
PublicationDecade	2020
PublicationTitle	IET image processing
PublicationYear	2024
Publisher	Wiley
Publisher_xml	– name: Wiley
References	2023; 53 2023; 32 2017; 64 2023; 35 2023; 33 2023; 11 2022; 71 2023; 163 2023; 7 2019; 78 2022; 45 2021; 52 2020; 8 2021; 11 2021; 33 2023 2022 2021 2020 2022; 9 2019; 138 2019 2008; 23 2018 2020; 69 2023; 136 2017 2016 2015 2018; 50 2014 2021; 452 2007; 22 e_1_2_9_30_1 e_1_2_9_31_1 e_1_2_9_11_1 e_1_2_9_34_1 e_1_2_9_10_1 e_1_2_9_35_1 e_1_2_9_13_1 e_1_2_9_32_1 e_1_2_9_12_1 e_1_2_9_33_1 Bochkovskiy A. (e_1_2_9_22_1) 2020 e_1_2_9_15_1 e_1_2_9_38_1 e_1_2_9_14_1 e_1_2_9_39_1 e_1_2_9_17_1 e_1_2_9_36_1 e_1_2_9_16_1 e_1_2_9_37_1 e_1_2_9_19_1 e_1_2_9_18_1 e_1_2_9_41_1 e_1_2_9_42_1 e_1_2_9_20_1 e_1_2_9_40_1 e_1_2_9_21_1 e_1_2_9_24_1 e_1_2_9_43_1 e_1_2_9_23_1 e_1_2_9_44_1 e_1_2_9_8_1 e_1_2_9_7_1 e_1_2_9_6_1 e_1_2_9_5_1 e_1_2_9_4_1 e_1_2_9_3_1 e_1_2_9_2_1 Zhang Z.‐D. (e_1_2_9_45_1) 2022; 71 e_1_2_9_9_1 e_1_2_9_26_1 e_1_2_9_25_1 e_1_2_9_28_1 e_1_2_9_27_1 e_1_2_9_29_1
References_xml	– start-page: 8510 year: 2021 end-page: 8519 article-title: VarifocalNet: an IoU‐aware dense object detector – volume: 23 start-page: 1183 issue: 2 year: 2008 end-page: 1190 article-title: Comparison of DC pollution flashover performances of various types of porcelain, glass, and composite insulators publication-title: IEEE Trans. Power Delivery – volume: 69 start-page: 9350 issue: 12 year: 2020 end-page: 9365 article-title: A review on state‐of‐the‐art power line inspection techniques publication-title: IEEE Trans. Instrum. Meas. – volume: 33 start-page: 2686 issue: 6 year: 2021 end-page: 2700 article-title: Neural schrödinger equation: physical law as deep neural network publication-title: IEEE Trans. Neural Networks Learn. Syst. – start-page: 658 year: 2019 end-page: 666 article-title: Generalized intersection over union: a metric and a loss for bounding box regression – volume: 78 start-page: 10097 year: 2019 end-page: 10112 article-title: Insulator self‐shattering detection: a deep convolutional neural network approach publication-title: Multimed. Tools Appl. – volume: 11 start-page: 257 issue: 2 year: 2023 article-title: Detection of bird nests on transmission towers in aerial images based on improved YOLOv5s publication-title: Machines – year: 2021 – start-page: 1 year: 2022 end-page: 6 article-title: Transmission line pin detection based on improved SSD – start-page: 805 year: 2022 end-page: 815 article-title: On the integration of self‐attention and convolution – volume: 45 start-page: 1489 issue: 2 year: 2022 end-page: 1500 article-title: Contextual transformer networks for visual recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 52 start-page: 8574 issue: 8 year: 2021 end-page: 8586 article-title: Enhancing geometric factors in model learning and inference for object detection and instance segmentation publication-title: IEEE Trans. Cybern. – volume: 11 start-page: 4647 issue: 10 year: 2021 article-title: Insulator faults detection in aerial images from high‐voltage transmission lines based on deep learning model publication-title: Appl. Sci. – year: 2023 article-title: Partial siamese with multiscale bi‐codec networks for remote sensing image haze removal publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 50 start-page: 1486 issue: 4 year: 2018 end-page: 1498 article-title: Detection of power line insulator defects using aerial images analyzed with convolutional neural networks publication-title: IEEE Trans. Syst. Man Cybern. Syst. – volume: 136 year: 2023 article-title: Coherence‐aware context aggregator for fast video object segmentation publication-title: Pattern Recognit. – volume: 7 start-page: 304 issue: 5 year: 2023 article-title: A modified YOLOv8 detection network for UAV aerial image recognition publication-title: Drones – volume: 8 start-page: 102907 year: 2020 end-page: 102919 article-title: Research on recognition of fly species based on improved RetinaNet and CBAM publication-title: IEEE Access – year: 2018 – volume: 9 start-page: 661 issue: 2 year: 2022 end-page: 691 article-title: State of the art in defect detection based on machine vision publication-title: Int. J. Precis. Eng. Manuf.‐Green Technol. – volume: 64 start-page: 9699 issue: 12 year: 2017 end-page: 9708 article-title: Acoustic fault detection technique for high‐power insulators publication-title: IEEE Trans. Ind. Electron. – volume: 33 start-page: 3899 year: 2023 end-page: 3911 article-title: Active learning with co‐auxiliary learning and multi‐level diversity for image classification publication-title: IEEE Trans. Circuits Syst. Video Technol. – volume: 32 start-page: 1966 year: 2023 end-page: 1977 article-title: Precise facial landmark detection by reference heatmap transformer publication-title: IEEE Trans. Image Process. – volume: 138 start-page: 379 year: 2019 end-page: 385 article-title: Intelligent fault detection of high voltage line based on the faster R‐CNN publication-title: Measurement – start-page: 580 year: 2014 end-page: 587 article-title: Rich feature hierarchies for accurate object detection and semantic segmentation – start-page: 91 year: 2015 end-page: 99 article-title: Faster R‐CNN: towards real‐time object detection with region proposal networks – volume: 53 start-page: 3546 issue: 6 year: 2023 end-page: 3560 article-title: Robust and precise facial landmark detection by self‐calibrated pose attention network publication-title: IEEE Trans. Cybern. – volume: 71 start-page: 1 year: 2022 end-page: 8 article-title: FINet: an insulator dataset and detection benchmark based on synthetic fog and improved YOLOv5 publication-title: IEEE Trans. Instrum. Meas. – year: 2022 – year: 2020 – start-page: 2999 year: 2017 end-page: 3007 article-title: Focal loss for dense object detection – year: 2023 – volume: 452 start-page: 48 year: 2021 end-page: 62 article-title: A review on the attention mechanism of deep learning publication-title: Neurocomputing – volume: 35 start-page: 3737 issue: 5 year: 2023 end-page: 3751 article-title: Scale‐free heterogeneous cycleGAN for defogging from a single image for autonomous driving in fog publication-title: Neural Comput. Appl. – start-page: 2778 year: 2021 end-page: 2788 article-title: TPH‐YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone‐captured scenarios – year: 2020 article-title: YOLOv4: optimal speed and accuracy of object detection publication-title: arXiv:200410934 – start-page: 12993 year: 2020 end-page: 13000 article-title: Distance‐IoU loss: faster and better learning for bounding box regression – volume: 163 start-page: 10 year: 2023 end-page: 27 article-title: Multi‐level feature interaction and efficient non‐local information enhanced channel attention for image dehazing publication-title: Neural Networks – start-page: 21 year: 2016 end-page: 37 article-title: SSD: single shot multibox detector – volume: 22 start-page: 2567 issue: 4 year: 2007 end-page: 2574 article-title: Study on AC artificial‐contaminated flashover performance of various types of insulators publication-title: IEEE Trans. Power Delivery – volume: 71 start-page: 1 year: 2022 end-page: 12 article-title: A fast and accurate method of power line intelligent inspection based on edge computing publication-title: IEEE Trans. Instrum. Meas. – ident: e_1_2_9_42_1 – ident: e_1_2_9_2_1 doi: 10.1109/TIM.2020.3031194 – ident: e_1_2_9_12_1 doi: 10.1109/TIP.2023.3261749 – ident: e_1_2_9_13_1 doi: 10.1007/s00521-021-06296-w – ident: e_1_2_9_7_1 doi: 10.1109/TIE.2017.2716862 – ident: e_1_2_9_39_1 doi: 10.1109/TCYB.2021.3095305 – ident: e_1_2_9_29_1 doi: 10.3390/drones7050304 – ident: e_1_2_9_27_1 doi: 10.1109/CVPR52688.2022.00089 – volume: 71 start-page: 1 year: 2022 ident: e_1_2_9_45_1 article-title: FINet: an insulator dataset and detection benchmark based on synthetic fog and improved YOLOv5 publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2022.3194909 – ident: e_1_2_9_33_1 doi: 10.1109/TPAMI.2022.3164083 – ident: e_1_2_9_9_1 doi: 10.1007/s40684-021-00343-6 – ident: e_1_2_9_34_1 doi: 10.1016/j.neucom.2021.03.091 – ident: e_1_2_9_14_1 doi: 10.1016/j.patcog.2022.109214 – ident: e_1_2_9_24_1 doi: 10.1109/TIM.2022.3219307 – ident: e_1_2_9_26_1 doi: 10.1109/TNNLS.2021.3120472 – ident: e_1_2_9_43_1 – ident: e_1_2_9_16_1 doi: 10.1109/TGRS.2023.3321307 – ident: e_1_2_9_25_1 doi: 10.1109/ACCESS.2020.2997466 – ident: e_1_2_9_4_1 doi: 10.1109/TPWRD.2007.899760 – ident: e_1_2_9_20_1 doi: 10.1007/978-3-319-46448-0_2 – ident: e_1_2_9_6_1 doi: 10.3390/app11104647 – ident: e_1_2_9_15_1 doi: 10.1109/TCSVT.2023.3234993 – ident: e_1_2_9_32_1 – ident: e_1_2_9_40_1 doi: 10.1109/CVPR46437.2021.00841 – ident: e_1_2_9_8_1 doi: 10.1007/s11042-018-6610-4 – ident: e_1_2_9_21_1 – ident: e_1_2_9_35_1 – ident: e_1_2_9_30_1 doi: 10.1109/ICCVW54120.2021.00312 – ident: e_1_2_9_41_1 doi: 10.1109/ICCV.2017.324 – ident: e_1_2_9_10_1 doi: 10.1109/TCYB.2021.3131569 – ident: e_1_2_9_44_1 – ident: e_1_2_9_17_1 doi: 10.1109/CVPR.2014.81 – ident: e_1_2_9_37_1 doi: 10.1109/CVPR.2019.00075 – ident: e_1_2_9_28_1 doi: 10.3390/machines11020257 – ident: e_1_2_9_38_1 doi: 10.1609/aaai.v34i07.6999 – ident: e_1_2_9_19_1 doi: 10.1016/j.measurement.2019.01.072 – ident: e_1_2_9_11_1 doi: 10.1016/j.patcog.2022.109214 – ident: e_1_2_9_18_1 – ident: e_1_2_9_23_1 – ident: e_1_2_9_31_1 doi: 10.1109/CVPR52729.2023.00721 – ident: e_1_2_9_3_1 doi: 10.1109/TPWRD.2007.908779 – ident: e_1_2_9_5_1 doi: 10.1109/TSMC.2018.2871750 – year: 2020 ident: e_1_2_9_22_1 article-title: YOLOv4: optimal speed and accuracy of object detection publication-title: arXiv:200410934 – ident: e_1_2_9_36_1 doi: 10.1016/j.neunet.2023.03.017
SSID	ssj0059085
Score	2.5380943
Snippet	The YOLO series of algorithms have made substantial contributions to the detection of insulator defects in power transmission line operations. However,... Abstract The YOLO series of algorithms have made substantial contributions to the detection of insulator defects in power transmission line operations....
SourceID	doaj crossref wiley
SourceType	Open Website Enrichment Source Index Database Publisher
StartPage	1096
SubjectTerms	computer vision image recognition insulators object detection
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iHrz4FtcXAb0oFNsmbRJvvhVERRT1VPLUxdqV3VU8-hP8jf4SJ2lXFEQv3koykJCZZGaayfchtBpTBm7Q5VEGOymiJJeRpJxEkjGZWhVLJ3Ugm2AnJ_z6Wpx9ofryNWE1PHC9cBvCpibWFKJkY6hLY-UfJwurRA5bXOfGn74xE4Nkqj6DPZF3Fp5CehL5PBMDYFIqNtqP3TRwIItvrigg9n-PUIOL2Z9AY01siLfqOU2iIVtNofEmTsTNLuxNo5fdg6v317eb0-PTZ76Jt3DvQZYlDmXlPofGdXk3NrYfCq0qLMvbTrfdv3vA3msZDE3GhnBVlRZ7iM1Q9Ai9-l51KmiqDL466lziEmaOvfPz_TPocn_vYucwahgUIk0h9YmYThJLDVEScuZUQSiiNVHcJZJZAbqw_q9PnKick9g6wpghTmnrYm6kcElCZtFwBaPOIZxILjPDQeeQEGZKSOuRzzgxkDPm2vEWWhssZqEbeHHPclEW4ZqbisIvfLg9Ey208in7WINq_Ci17XXyKeGBsEMDmEfRmEfxl3m00HrQ6C_jFEdn52n4mv-PERfQaAqBT12ntoiG-90nu4RG9HO_3esuBzP9ADrC7AM priority: 102 providerName: Directory of Open Access Journals
Title	DGW‐YOLOv8: A small insulator target detection algorithm based on deformable attention backbone and WIoU loss function
URI	https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fipr2.13009 https://doaj.org/article/9e2d0c4428dd4f20b81809eb96467c6d
Volume	18
WOSCitedRecordID	wos001124609100001&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: 1751-9667 dateEnd: 20241231 omitProxy: false ssIdentifier: ssj0059085 issn: 1751-9659 databaseCode: DOA dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVWIB databaseName: Wiley Online Library Free Content customDbUrl: eissn: 1751-9667 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0059085 issn: 1751-9659 databaseCode: WIN dateStart: 20130101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Open Access customDbUrl: eissn: 1751-9667 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0059085 issn: 1751-9659 databaseCode: 24P dateStart: 20130101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NbtQwELZK4cCF8iu2hcoSXIoUkcRObCMuLbSwEtquKqotp8i_ZUWarbJL1WMfgWfkSTrjZLeqhJAQlyiyJ3KSmfHM2ONvCHmdcgFmMJRJAZqUcFbqRHPJEi2Ezr1JddA2FpsQo5E8OVHjNfJ-eRamw4dYLbihZsT5GhVcm64KCTi1wMTpeZvHWsbqDrmbZUygTOd8vJyHsZh3EY9DYiH5slBLcFKu3t48e8scRdT-215qNDMHG__3gg_Jg969pLudPDwia755TDZ6V5P2ijx_Qi4_fpr8vvr17fDL4YV8R3fp_EzXNY2Z6RiG0y5DnDq_iLlaDdX16aydLr6fUTR8jkKT89HjNbWniNIZ8yah1_4wswaaGkcnw9kxreHDKdpP7H9Kjg_2v374nPRFGBLLIXpKhM0yzx0zGsLu3IA3Yy0zMmRaeAXs9LhwlGamlCz1gQnhWDDWh1Q6rQLw5RlZb2DU54RmWurCSRAbiCkLo7RH8DTJHISdpQ1yQHaWvKhsj1COhTLqKu6Uc1XhL40bcGpAXq1ozztcjj9S7SFLVxSIpR0bZu1p1atmpXzuUsshDnOOhzw1ePxdeaNKMCK2dAPyJrL5L-NUw_FRHu82_4V4i9zPwUfqUtpekPVF-9O_JPfsxWI6b7ejNG_HRQK4ToajaxvX-n0
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fT9RAEN8gmugLiH_iIeAm-qJJY9vdtru-IYpcOI-LgYBPzf7FC6VHegfx0Y_AZ_STMLPtHSExJsa3ZjvNtp2d_c3szv6GkDcxLwAGfR5lYEkRZ7mKFBcsUkWhUqdj5ZUJxSaK4VCcnMhRl5uDZ2FafojFghtaRpiv0cBxQboNODmSZI4vmjQUM5b3yH0OMIMFDFI-mk_EWM07C-chsZJ8nsk5OymX72-fvYNHgbb_rpsacGZ39T_f8DFZ6RxMut2OiDWy5OonZLVzNmlnytOn5OenL8e_f11_PxgcXIkPdJtOz1VV0ZCbjoE4bXPEqXWzkK1VU1WdTprx7Mc5ReizFJqsCz6vrhxFns6QOQl3zZme1NBUW3rcnxzRCr6cIoLi_WfkaPfz4c5e1JVhiAyH-CkqTJI4bplWEHinGvwZY5gWPlGFk6BQh0tHcaJzwWLnWVFY5rVxPhZWSZ8k7DlZrqHXF4QmSqjMChg4EFVmWiqH9GmCWQg8c-NFj7ydK6M0HUc5lsqoyrBXzmWJvzRswckeeb2QvWiZOf4o9RF1upBANu3QMGlOy844S-lSGxsOkZi13KexxgPw0mmZA4yY3PbIu6Dnv_RT9kff0nC1_i_Cr8jDvcOvg3LQH-6_JI9S8JjaBLcNsjxrLt0meWCuZuNpsxWG9g0jLPxb
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwELYoVBUX6FMs9GGpvbRS1CR2Ers3Wrp0VbSsqiLoKfKTrgjZVXZBHPsT-I38ks442UVIVaWqt8iZyEnG45nPHn9DyJuYF-AGfR5lYEkRZ7mKFBcsUkWhUqdj5ZUJxSaK4VCcnMhRl5uDZ2FafojlghtaRpiv0cDd1PoWcHIkyRxPmzQUM5b3yBrPYJJFYmc-WkzEWM07C-chsZJ8nskFOymX72-fveOPAm3_3TA1-Jn-5n--4UOy0QWYdLcdEY_Iiqsfk80u2KSdKc-ekKu9_eObX9c_Dg8OL8UHuktn56qqaMhNRyBO2xxxat08ZGvVVFWnk2Y8_3lO0fVZCk3WhZhXV44iT2fInIS75kxPamiqLT0eTI5oBV9O0YPi_afkqP_5-6cvUVeGITIc8FNUmCRx3DKtAHinGuIZY5gWPlGFk6BQh0tHcaJzwWLnWVFY5rVxPhZWSZ8k7BlZraHXLUITJVRmBQwcQJWZlsohfZpgFoBnbrzokbcLZZSm4yjHUhlVGfbKuSzxl4YtONkjr5ey05aZ449SH1GnSwlk0w4Nk-a07IyzlC61seGAxKzlPo01HoCXTssc3IjJbY-8C3r-Sz_lYPQtDVfb_yL8ijwY7fXLg8Hw6w5ZTyFgavPbnpPVeXPhXpD75nI-njUvw8j-Dc0p-98
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=DGW%E2%80%90YOLOv8%3A+A+small+insulator+target+detection+algorithm+based+on+deformable+attention+backbone+and+WIoU+loss+function&rft.jtitle=IET+image+processing&rft.au=Hu%2C+Deao&rft.au=Yu%2C+Mei&rft.au=Wu%2C+Xianyong&rft.au=Hu%2C+Jingbo&rft.date=2024-03-01&rft.issn=1751-9659&rft.eissn=1751-9667&rft.volume=18&rft.issue=4&rft.spage=1096&rft.epage=1108&rft_id=info:doi/10.1049%2Fipr2.13009&rft.externalDBID=n%2Fa&rft.externalDocID=10_1049_ipr2_13009
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9659&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9659&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9659&client=summon