Object detection based on RGC mask R-CNN
Object detection is a crucial topic in computer vision. Mask Region-Convolution Neural Network (R-CNN) based methods, wherein a large intersection over union (IoU) threshold is chosen for high quality samples, have often been employed for object detection. However, the detection performance of such...
Uloženo v:
| Vydáno v: | IET image processing Ročník 14; číslo 8; s. 1502 - 1508 |
|---|---|
| Hlavní autoři: | , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
The Institution of Engineering and Technology
19.06.2020
|
| Témata: | |
| 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 | Object detection is a crucial topic in computer vision. Mask Region-Convolution Neural Network (R-CNN) based methods, wherein a large intersection over union (IoU) threshold is chosen for high quality samples, have often been employed for object detection. However, the detection performance of such methods deteriorates when samples are reduced. To address this, the authors propose an improved Mask R-CNN-based method: the ResNet Group Cascade (RGC) Mask R-CNN. First, they compared ResNet with different layers, finding that ResNeXt-101-64 × 4d is superior to other backbone networks. Secondly, during the training of the test model, the performance of Mask R-CNN suffered from a small batch processing scale, resulting in inaccurately calculated mean and variance; thus, group normalisation was added to the backbone, feature pyramid network neck and bounding box head of the network. Finally, the higher the intersection of Mask R-CNN than the threshold, the easier it is to obtain high-quality samples. However, blindly selecting a high threshold leads to sample reduction and overfitting. Thus, a proposed cascade network configuration with three IoU thresholds was utilised in the process of model training. The model was trained and tested on the COCO and PASCAL VOC07 datasets. Their proposed algorithm demonstrated superior performance compared to that of the Mask R-CNN. |
|---|---|
| AbstractList | Object detection is a crucial topic in computer vision. Mask Region‐Convolution Neural Network (R‐CNN) based methods, wherein a large intersection over union (IoU) threshold is chosen for high quality samples, have often been employed for object detection. However, the detection performance of such methods deteriorates when samples are reduced. To address this, the authors propose an improved Mask R‐CNN‐based method: the ResNet Group Cascade (RGC) Mask R‐CNN. First, they compared ResNet with different layers, finding that ResNeXt‐101‐64 × 4d is superior to other backbone networks. Secondly, during the training of the test model, the performance of Mask R‐CNN suffered from a small batch processing scale, resulting in inaccurately calculated mean and variance; thus, group normalisation was added to the backbone, feature pyramid network neck and bounding box head of the network. Finally, the higher the intersection of Mask R‐CNN than the threshold, the easier it is to obtain high‐quality samples. However, blindly selecting a high threshold leads to sample reduction and overfitting. Thus, a proposed cascade network configuration with three IoU thresholds was utilised in the process of model training. The model was trained and tested on the COCO and PASCAL VOC07 datasets. Their proposed algorithm demonstrated superior performance compared to that of the Mask R‐CNN. |
| Author | Yue, Hanhui Huang, Yongxi Wu, Minghu Ke, Cong Liu, Min Wang, Juan Zeng, Cheng Jiang, Yuhan |
| Author_xml | – sequence: 1 givenname: Minghu surname: Wu fullname: Wu, Minghu organization: 2Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Wuhan 430068, People's Republic of China – sequence: 2 givenname: Hanhui surname: Yue fullname: Yue, Hanhui organization: 2Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Wuhan 430068, People's Republic of China – sequence: 3 givenname: Juan surname: Wang fullname: Wang, Juan email: happywj@hbut.edu.cn organization: 3Post-doctoral Research Workstation, Wuhan Huaan Science and Technology Co., Ltd., Wuhan 430068, People's Republic of China – sequence: 4 givenname: Yongxi surname: Huang fullname: Huang, Yongxi organization: 2Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Wuhan 430068, People's Republic of China – sequence: 5 givenname: Min surname: Liu fullname: Liu, Min organization: 2Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Wuhan 430068, People's Republic of China – sequence: 6 givenname: Yuhan surname: Jiang fullname: Jiang, Yuhan organization: 2Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Wuhan 430068, People's Republic of China – sequence: 7 givenname: Cong surname: Ke fullname: Ke, Cong organization: 2Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Wuhan 430068, People's Republic of China – sequence: 8 givenname: Cheng surname: Zeng fullname: Zeng, Cheng organization: 2Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Wuhan 430068, People's Republic of China |
| BookMark | eNqFkE1PwjAYgBuDiYD-AG876mHYrlu7etMFkISAIXhu-vEuKcJGuhnDv6cLxhjjx-l9D8_T9ukA9aq6AoSuCR4RnIo7B23s9n6UYCJGGGf8DPUJz0gsGOO9zz0TF2jQNJtACJxnfXSz1BswbWShDcPVVaRVAzYKy2paRDvVvEaruFgsLtF5qbYNXH3MIXqZjNfFUzxfTmfFwzw2KSE0NkJbC5ARTllpS2F4kjDQkGoCKc21wqVK0owZRjXXmvEcjCgB29TmSlhDh4iczjW-bhoPpdx7t1P-IAmWXaoMqTKkyi5VdqnB4d8c41rV1bReue2f5v3JfHdbOPx_lZw9r5LHCU4oo0G-PckdtqnffBU-Rs7G64764uxtGdj4B_b3hx0BpjmK7g |
| CitedBy_id | crossref_primary_10_1016_j_jfranklin_2020_07_045 crossref_primary_10_1088_1361_6501_ad3f3a crossref_primary_10_1002_acs_3287 crossref_primary_10_1002_acs_3320 crossref_primary_10_1002_acs_3169 crossref_primary_10_1002_acs_3203 crossref_primary_10_1002_oca_2766 crossref_primary_10_1155_2023_1135946 crossref_primary_10_12688_f1000research_73156_1 crossref_primary_10_12688_f1000research_73156_2 crossref_primary_10_1016_j_jfranklin_2020_08_045 crossref_primary_10_1007_s11071_021_06730_7 crossref_primary_10_3390_electronics12183760 crossref_primary_10_1007_s12555_020_0688_y crossref_primary_10_1007_s12555_019_1060_y crossref_primary_10_1155_2022_7811200 crossref_primary_10_1002_rnc_5266 crossref_primary_10_1109_JSEN_2024_3524584 crossref_primary_10_1080_10106049_2022_2036824 crossref_primary_10_1049_cth2_12161 crossref_primary_10_1002_rnc_5206 crossref_primary_10_1002_rnc_5646 crossref_primary_10_1155_2022_5785108 crossref_primary_10_1007_s12145_022_00834_3 crossref_primary_10_1061_JCCEE5_CPENG_5948 crossref_primary_10_1002_acs_3296 crossref_primary_10_1002_acs_3257 crossref_primary_10_1049_iet_cta_2020_0673 crossref_primary_10_1002_rnc_5576 crossref_primary_10_1016_j_jclepro_2022_131096 crossref_primary_10_1016_j_jafr_2024_101139 crossref_primary_10_3390_buildings14041129 crossref_primary_10_1080_00207721_2021_1889707 crossref_primary_10_1002_acs_3308 crossref_primary_10_1002_acs_3221 crossref_primary_10_1049_iet_cta_2020_0866 crossref_primary_10_1002_acs_3263 crossref_primary_10_1002_acs_3302 crossref_primary_10_1109_ACCESS_2024_3407720 crossref_primary_10_32604_cmc_2023_039582 crossref_primary_10_3390_s22187026 crossref_primary_10_1007_s11277_024_11539_9 crossref_primary_10_1088_1755_1315_1276_1_012073 crossref_primary_10_1007_s12555_019_0831_9 crossref_primary_10_1007_s11554_021_01182_z crossref_primary_10_1002_rnc_5200 crossref_primary_10_3103_S8756699024700146 crossref_primary_10_1007_s00034_021_01801_x crossref_primary_10_1049_cth2_12118 crossref_primary_10_1049_iet_ipr_2020_1128 crossref_primary_10_1109_ACCESS_2025_3583341 crossref_primary_10_1002_rnc_5706 crossref_primary_10_1002_rnc_5468 crossref_primary_10_1002_mp_17176 crossref_primary_10_1016_j_sigpro_2020_107904 crossref_primary_10_1049_ipr2_12280 crossref_primary_10_1016_j_jfranklin_2021_04_006 crossref_primary_10_3390_aerospace8040112 crossref_primary_10_3390_s24134347 crossref_primary_10_3390_buildings14020420 crossref_primary_10_1002_rnc_5675 crossref_primary_10_1016_j_jclepro_2023_137558 crossref_primary_10_1016_j_jfranklin_2021_01_020 crossref_primary_10_1049_ipr2_12318 crossref_primary_10_1002_rnc_5672 crossref_primary_10_1109_ACCESS_2022_3190969 crossref_primary_10_1007_s11554_021_01178_9 |
| Cites_doi | 10.1109/ICCV.2015.135 10.1109/CVPR.2015.7298642 10.1007/978-3-319-10584-0_20 10.1109/CVPR.2015.7299170 10.1109/ICCV.2017.322 10.1109/CVPR.2017.243 10.1109/CVPR.2014.81 10.1049/iet-ipr.2017.1144 10.1109/ICCV.2015.169 10.1049/iet-ipr.2018.5424 10.1109/CVPR.2016.343 10.1109/CVPR.2015.7298965 10.1109/CVPR.2001.990517 10.1109/CVPR.2017.634 10.1109/CVPR.2016.90 10.1109/ICCV.2017.593 10.1109/TPAMI.2016.2577031 |
| ContentType | Journal Article |
| Copyright | The Institution of Engineering and Technology 2021 The Authors. IET Image Processing published by John Wiley & Sons, Ltd. on behalf of The Institution of Engineering and Technology |
| Copyright_xml | – notice: The Institution of Engineering and Technology – notice: 2021 The Authors. IET Image Processing published by John Wiley & Sons, Ltd. on behalf of The Institution of Engineering and Technology |
| DBID | AAYXX CITATION |
| DOI | 10.1049/iet-ipr.2019.0057 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISSN | 1751-9667 |
| EndPage | 1508 |
| ExternalDocumentID | 10_1049_iet_ipr_2019_0057 IPR2BF02363 |
| Genre | article |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 6160117 – fundername: Major Technological Innovation Projects of Hubei grantid: 2018AAA028 – fundername: Hubei university outstanding youth science and technology innovation team project grantid: T201805 – fundername: National Natural Science Foundation of China grantid: 61901165 – fundername: Hubei University of Technology Ph.D. Research Startup Fund Project grantid: BSQD2015023 – fundername: Hubei Provincial Department of Education Scientific Research Project Funded Project Young Talents Program grantid: Q20181401 – fundername: National Natural Science Foundation of China funderid: 6160117; 61901165 |
| GroupedDBID | 0R 24P 29I 5GY 6IK 8VB AAJGR ABPTK ACGFS ACIWK AENEX ALMA_UNASSIGNED_HOLDINGS BFFAM CS3 DU5 ESX HZ IFIPE IPLJI JAVBF LAI M43 MS O9- OCL P2P QWB RIE RNS RUI UNR ZL0 .DC 0R~ 1OC 4.4 8FE 8FG AAHHS AAHJG ABJCF ABQXS ACCFJ ACCMX ACESK ACXQS ADZOD AEEZP AEQDE AFKRA AIWBW AJBDE ALUQN ARAPS AVUZU BENPR BGLVJ CCPQU EBS EJD GROUPED_DOAJ HCIFZ HZ~ IAO ITC K1G L6V M7S MCNEO MS~ OK1 P62 PTHSS ROL S0W AAMMB AAYXX AEFGJ AFFHD AGXDD AIDQK AIDYY CITATION IDLOA PHGZM PHGZT PQGLB WIN |
| ID | FETCH-LOGICAL-c4113-c9bddee51736fdf9c7226ebe4b1e438ba0fa2456c63b7bb678ec9fe0d4d8a9dc3 |
| IEDL.DBID | 24P |
| ISICitedReferencesCount | 76 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000537949300008&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 | Wed Oct 29 21:14:30 EDT 2025 Tue Nov 18 22:30:01 EST 2025 Wed Jan 22 16:32:18 EST 2025 Sat May 30 04:20:32 EDT 2020 Tue Jan 05 21:50:47 EST 2021 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Keywords | image classification detection performance improved Mask R-CNN-based method object detection high quality samples bounding box head feature extraction ResNet Group Cascade Mask R-CNN computer vision image representation RGC mask R-CNN feature pyramid network neck Mask Region-Convolution Neural Network based methods learning (artificial intelligence) high-quality samples image coding neural nets |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4113-c9bddee51736fdf9c7226ebe4b1e438ba0fa2456c63b7bb678ec9fe0d4d8a9dc3 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/iet-ipr.2019.0057 |
| PageCount | 7 |
| ParticipantIDs | crossref_citationtrail_10_1049_iet_ipr_2019_0057 crossref_primary_10_1049_iet_ipr_2019_0057 wiley_primary_10_1049_iet_ipr_2019_0057_IPR2BF02363 iet_journals_10_1049_iet_ipr_2019_0057 |
| ProviderPackageCode | RUI |
| PublicationCentury | 2000 |
| PublicationDate | 2020-06-19 |
| PublicationDateYYYYMMDD | 2020-06-19 |
| PublicationDate_xml | – month: 06 year: 2020 text: 2020-06-19 day: 19 |
| PublicationDecade | 2020 |
| PublicationTitle | IET image processing |
| PublicationYear | 2020 |
| Publisher | The Institution of Engineering and Technology |
| Publisher_xml | – name: The Institution of Engineering and Technology |
| References | Wu, K.; Yu, Y. (C7) 2018; 12 Tang, L.; Gao, C.; Chen, X. (C6) 2018; 12 Ren, S.; He, K.; Girshick, R. (C9) 2016; 39 Rehman, Y.; Khan, J.; Shin, H. (C12) 2018; 12 2018; 6 June 2014 2016; 10 June 2015 2018 June 2016 2017 2016 9 September 2014 7 July 2017 2014 2013 2018; 12 10 July 2017; 3 2016; 39 10 July 2017 1 December 2001 e_1_2_7_6_1 e_1_2_7_5_1 e_1_2_7_4_1 e_1_2_7_3_1 e_1_2_7_9_1 e_1_2_7_8_1 e_1_2_7_19_1 Tang L. (e_1_2_7_7_1) 2018; 12 e_1_2_7_18_1 e_1_2_7_17_1 e_1_2_7_16_1 e_1_2_7_2_1 e_1_2_7_15_1 e_1_2_7_14_1 e_1_2_7_13_1 e_1_2_7_12_1 e_1_2_7_11_1 e_1_2_7_10_1 e_1_2_7_26_1 e_1_2_7_27_1 e_1_2_7_28_1 e_1_2_7_29_1 e_1_2_7_30_1 e_1_2_7_25_1 e_1_2_7_31_1 e_1_2_7_24_1 e_1_2_7_23_1 e_1_2_7_22_1 e_1_2_7_21_1 e_1_2_7_20_1 |
| References_xml | – volume: 39 start-page: 1137 issue: 6 year: 2016 end-page: 1149 ident: C9 article-title: Faster R-CNN: towards real-time object detection with region proposal networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 12 start-page: 1131 issue: 7 year: 2018 end-page: 1141 ident: C6 article-title: Pose detection in complex classroom environment based on improved faster R-CNN publication-title: IET Image Process. – volume: 12 start-page: 1131 year: 2018 end-page: 1141 ident: C7 article-title: Automatic object extraction from images using deep neural networks and the level-set method publication-title: IET Image Process. – volume: 12 start-page: 2229 issue: 12 year: 2018 end-page: 2237 ident: C12 article-title: Efficient coarser-to-fine holistic traffic sign detection for occlusion handling publication-title: IET Image Process. – start-page: 5562 year: 10 July 2017 end-page: 5570 – start-page: 5325 year: June 2015 end-page: 5334 – volume: 12 start-page: 1131 issue: 7 year: 2018 end-page: 1141 article-title: Pose detection in complex classroom environment based on improved faster R‐CNN publication-title: IET Image Process. – start-page: 2874 year: June 2016 end-page: 2883 – start-page: 770 year: June 2016 end-page: 778 – start-page: 2980 year: 10 July 2017 end-page: 2988 – start-page: 1134 year: June 2015 end-page: 1142 – start-page: I‐I year: 1 December 2001 – volume: 12 start-page: 2229 issue: 12 year: 2018 end-page: 2237 article-title: Efficient coarser‐to‐fine holistic traffic sign detection for occlusion handling publication-title: IET Image Process. – volume: 10 start-page: 21 year: 2016 end-page: 37 – volume: 3 start-page: 7 issue: 6 year: 10 July 2017 – year: 2018 – start-page: 779 year: June 2016 end-page: 788 – year: 2014 – start-page: 3 year: 7 July 2017 – start-page: 5987 year: 7 July 2017 end-page: 5995 – start-page: 580 year: June 2014 end-page: 587 – volume: 12 start-page: 1131 year: 2018 end-page: 1141 article-title: Automatic object extraction from images using deep neural networks and the level‐set method publication-title: IET Image Process. – start-page: 1440 year: June 2015 end-page: 1448 – start-page: 447 year: June 2015 end-page: 456 – volume: 39 start-page: 1137 issue: 6 year: 2016 end-page: 1149 article-title: Faster R‐CNN: towards real‐time object detection with region proposal networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 3431 year: June 2015 end-page: 3440 – start-page: 297 year: 9 September 2014 end-page: 312 – start-page: 789 year: June 2016 end-page: 798 – start-page: 379 year: 2016 end-page: 387 – year: 2017 – start-page: 3150 year: June 2016 end-page: 3158 – volume: 6 start-page: 10 year: 2018 end-page: 18 – year: 2013 – ident: e_1_2_7_20_1 – ident: e_1_2_7_3_1 doi: 10.1109/ICCV.2015.135 – ident: e_1_2_7_12_1 doi: 10.1109/CVPR.2015.7298642 – ident: e_1_2_7_29_1 – ident: e_1_2_7_14_1 doi: 10.1007/978-3-319-10584-0_20 – ident: e_1_2_7_19_1 doi: 10.1109/CVPR.2015.7299170 – ident: e_1_2_7_11_1 doi: 10.1109/ICCV.2017.322 – ident: e_1_2_7_22_1 doi: 10.1109/CVPR.2017.243 – ident: e_1_2_7_2_1 doi: 10.1109/CVPR.2014.81 – ident: e_1_2_7_28_1 – ident: e_1_2_7_8_1 doi: 10.1049/iet-ipr.2017.1144 – ident: e_1_2_7_9_1 doi: 10.1109/ICCV.2015.169 – ident: e_1_2_7_13_1 doi: 10.1049/iet-ipr.2018.5424 – ident: e_1_2_7_4_1 – ident: e_1_2_7_18_1 doi: 10.1109/CVPR.2016.343 – ident: e_1_2_7_5_1 – ident: e_1_2_7_15_1 doi: 10.1109/CVPR.2015.7298965 – ident: e_1_2_7_16_1 – ident: e_1_2_7_21_1 – ident: e_1_2_7_30_1 – ident: e_1_2_7_24_1 – ident: e_1_2_7_17_1 doi: 10.1109/CVPR.2001.990517 – ident: e_1_2_7_25_1 doi: 10.1109/CVPR.2017.634 – ident: e_1_2_7_27_1 – ident: e_1_2_7_23_1 doi: 10.1109/CVPR.2016.90 – ident: e_1_2_7_26_1 doi: 10.1109/ICCV.2017.593 – ident: e_1_2_7_6_1 – volume: 12 start-page: 1131 issue: 7 year: 2018 ident: e_1_2_7_7_1 article-title: Pose detection in complex classroom environment based on improved faster R‐CNN publication-title: IET Image Process. – ident: e_1_2_7_10_1 doi: 10.1109/TPAMI.2016.2577031 – ident: e_1_2_7_31_1 |
| SSID | ssj0059085 |
| Score | 2.5131845 |
| Snippet | Object detection is a crucial topic in computer vision. Mask Region-Convolution Neural Network (R-CNN) based methods, wherein a large intersection over union... Object detection is a crucial topic in computer vision. Mask Region‐Convolution Neural Network (R‐CNN) based methods, wherein a large intersection over union... |
| SourceID | crossref wiley iet |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 1502 |
| SubjectTerms | bounding box head computer vision detection performance feature extraction feature pyramid network neck high quality samples image classification image coding image representation improved Mask R‐CNN‐based method learning (artificial intelligence) Mask Region‐Convolution Neural Network based methods neural nets object detection Research Article ResNet Group Cascade Mask R‐CNN RGC mask R‐CNN |
| Title | Object detection based on RGC mask R-CNN |
| URI | http://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2019.0057 https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fiet-ipr.2019.0057 |
| Volume | 14 |
| WOSCitedRecordID | wos000537949300008&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 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 – providerCode: PRVWIB databaseName: Wiley Online Library Open Access 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 |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8NAEB60evDiW6wvgogHIZhkk-7uUYPVXmIpit7CPqGosbTRsz_B3-gvcSdNK0VQEC8hJDNJmJ3Zmd3Nfh_AkaFKMBIbnyD8o8vH1OeRTnwdBcKEgbCBVRXZBM0ydn_Pu3OQTvbCjPEhphNuGBlVf40BLuSYhcQVta4R-6b0-wOE9AwRcjKh87AQhoSia0dxd9IdI6d3Uu2KRD75VsKnS5v89NsjZpLTvLs9W7JWOae98i9fuwrLdcnpnY19ZA3mTLEOK3X56dXBPdqAk2uJkzKeNmX1f1bhYYrTnjvpXabekxg9eL2Pt_c0yzbhtn1xk175NZWCr2JnFF9x6foxk4SUtKy2XFFXdrn2i2VoYsKkCKzAJVDVIpJK6TKYUdyaQMeaCa4V2YJG8VyYbfA4w4xGmFaMxYnmwtiQUaFdYSmtkaoJwcSGuapxxpHu4jGv1rtjnjtb5M4WOdoiR1s04WSqMhiDbPwkfIzX6lAb_SR4OCPYubjJO93el0A-0LYJpGq239-LutF5GxH3yc6ftHZhKcLROjIf8T1olMMXsw-L6rXsj4YHlde6410n-wQ2R-9P |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1ba9swFD6kF-helq4XlnVtTRl9KJjalhxLj12aNKGZF0IKfRO6QmiXhSbb837CfmN_SXUcJyUUUih9M_aRLY509B1J1vcBfLOZloxQGxKkf_R4nIU8MWlokkjaOJIucroQm8jynN3e8l4FLudnYWb8EIsFN4yMYrzGAMcF6dmEkyJJ5tBOw-EYOT1j5JxMszXYoB5tUMcgob35eIyi3mlxLBIF5espX-xt8vMXr1hCpzX_eDlnLUCnVX2f6m7DxzLpDC5mveQTVOxoB6plAhqU4T3ZhbOfCpdlAmOnxR9aowBBzgT-on_VCH7JyV3Qf_z3v5Hne3DTag4a7bAUUwg1jWMSaq78SGbTOCN1ZxzXmU-8fAtSFVtKmJKRk7gJqutEZUp5DLOaOxsZapjkRpN9WB_9HtnPEHCGmEaY0YzR1HBpXcwyaXxqqZxVugbR3IlCl0zjKHhxL4odb8qF94XwvhDoC4G-qMHZosh4RrOxyvgU75XBNllleLJk2GkORKfXfzYQY-NqQIp2e_27WDb53kLOffLlTaWOYas9-NEV3U5-fQAfEpy7ow4S_wrr04c_9hA29d_pcPJwVHThJ8iZ8iI |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8NAEB58IV6sT6zPIOJBCCbdTbN71NZqUWIpCt6WfUJRa7HVsz_B3-gvcSdNK0VQEG8hmUmWmZ3H7mS_ATiwqZaMUBsShH_08TgNecUkoalE0saRdJHTebOJNMvY3R1vTUF9dBZmiA8x3nBDy8j9NRq47Rk3XHBSBMns2EHY6SGmZ4yYk0k6DbM08b4W8Z1pa-SPsal3kh-LxIby1YSPa5v8-NsrJqLTtH88mbPmQadR-p_hLsFikXQGJ8NZsgxTtrsCpSIBDQrz7q_C0bXCbZnA2EH-h1Y3wCBnAn_RPq8Fj7J_H7Q_3t5rWbYGt42zm9pFWDRTCDWNYxJqrrwns0mckqozjuvUJ15eg1TFlhKmZOQkFkF1lahUKR_DrObORoYaJrnRZB1muk9duwEBZxjTCDOaMZoYLq2LWSqNTy2Vs0qXIRoJUegCaRwbXjyIvOJNufCyEF4WAmUhUBZlOBqz9IYwGz8RH-K9wtj6PxHuTxA2z25Es9X-IhBeRWUgud5-_y7yVk4biLlPNv_EtQfzrXpDXDWzyy1YqODSHdsg8W2YGTy_2B2Y06-DTv95N5_Bn3_S8aY |
| 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=Object+detection+based+on+RGC+mask+R-CNN&rft.jtitle=IET+image+processing&rft.au=Wu%2C+Minghu&rft.au=Yue%2C+Hanhui&rft.au=Wang%2C+Juan&rft.au=Huang%2C+Yongxi&rft.date=2020-06-19&rft.pub=The+Institution+of+Engineering+and+Technology&rft.issn=1751-9659&rft.eissn=1751-9667&rft.volume=14&rft.issue=8&rft.spage=1502&rft.epage=1508&rft_id=info:doi/10.1049%2Fiet-ipr.2019.0057&rft.externalDocID=10_1049_iet_ipr_2019_0057 |
| 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 |