Object detection in factory based on deep learning approach
Manufacturing systems need to be highly adaptive and flexible to meet heterogeneous customer requirements and require fast and accurate object identification. This paper presents the implementation of deep learning for the object detection in a factory in which images of machines are used to train f...
Saved in:
| Published in | Procedia CIRP Vol. 104; pp. 1029 - 1034 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
2021
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Manufacturing systems need to be highly adaptive and flexible to meet heterogeneous customer requirements and require fast and accurate object identification. This paper presents the implementation of deep learning for the object detection in a factory in which images of machines are used to train four models. For each model, three trials with different hyperparameter configurations are performed. After the training, evaluations based on the loss curves, mean average precision curves, and performance metrics are carried out. Finally, the trained models are tested with a video in order to select the model with the best detection performance and accuracy. |
|---|---|
| AbstractList | Manufacturing systems need to be highly adaptive and flexible to meet heterogeneous customer requirements and require fast and accurate object identification. This paper presents the implementation of deep learning for the object detection in a factory in which images of machines are used to train four models. For each model, three trials with different hyperparameter configurations are performed. After the training, evaluations based on the loss curves, mean average precision curves, and performance metrics are carried out. Finally, the trained models are tested with a video in order to select the model with the best detection performance and accuracy. |
| Author | Aurich, Jan C. Yi, Li Siedler, Carina Kölsch, Patrick Glatt, Moritz Kinkel, Yann |
| Author_xml | – sequence: 1 givenname: Li surname: Yi fullname: Yi, Li email: li.yi@mv.uni-kl.de organization: Institute for Manufacturing Technology and Production Systems (FBK) of TU Kaiserslautern, P.O. Box 3049 Kaiserslautern, Germany – sequence: 2 givenname: Carina surname: Siedler fullname: Siedler, Carina organization: Institute for Manufacturing Technology and Production Systems (FBK) of TU Kaiserslautern, P.O. Box 3049 Kaiserslautern, Germany – sequence: 3 givenname: Yann surname: Kinkel fullname: Kinkel, Yann organization: Institute for Manufacturing Technology and Production Systems (FBK) of TU Kaiserslautern, P.O. Box 3049 Kaiserslautern, Germany – sequence: 4 givenname: Moritz surname: Glatt fullname: Glatt, Moritz organization: Institute for Manufacturing Technology and Production Systems (FBK) of TU Kaiserslautern, P.O. Box 3049 Kaiserslautern, Germany – sequence: 5 givenname: Patrick surname: Kölsch fullname: Kölsch, Patrick organization: Institute for Manufacturing Technology and Production Systems (FBK) of TU Kaiserslautern, P.O. Box 3049 Kaiserslautern, Germany – sequence: 6 givenname: Jan C. surname: Aurich fullname: Aurich, Jan C. organization: Institute for Manufacturing Technology and Production Systems (FBK) of TU Kaiserslautern, P.O. Box 3049 Kaiserslautern, Germany |
| BookMark | eNqFUMtKBDEQDLKC67p_4CE_MGMe81JBkMVVYWEveg6ZTkczjJkhGYT9e7OMB_GgTUE3DVVdXedk4QePhFxylnPGq6suH8MALuSCCZ7zhFqekKUQXGSNqPnix3xG1jF2LFVdMMnFktzu2w5hogan1NzgqfPUapiGcKCtjmho2hnEkfaog3f-jeoxXdTwfkFOre4jrr_7irxuH142T9lu__i8ud9lIEsxZcALYFUyp6GqrG2NAWHKSgDURcFZU7bMikYCa7W9tkaYVmosbWMlAwuSyxW5mXUhDDEGtArcpI9mp6BdrzhTxyRUp-Yk1DEJxRNqmcjFL_IY3IcOh_9odzMN02OfDoOK4NADGhdSUMoM7m-BLyX4fRM |
| CitedBy_id | crossref_primary_10_1007_s10845_024_02411_5 |
| Cites_doi | 10.1007/s11465-018-0499-5 10.1007/s00170-016-8628-y 10.1007/s00170-006-0897-4 10.1016/j.promfg.2020.01.052 10.1016/j.procir.2017.03.078 |
| ContentType | Journal Article |
| Copyright | 2021 |
| Copyright_xml | – notice: 2021 |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.procir.2021.11.173 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2212-8271 |
| EndPage | 1034 |
| ExternalDocumentID | 10_1016_j_procir_2021_11_173 S2212827121010714 |
| GroupedDBID | 0R~ 0SF 4.4 457 6I. AACTN AAEDT AAEDW AAFTH AAIKJ AALRI AAXUO ABMAC ACGFS ADBBV ADEZE AEXQZ AFTJW AGHFR AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ EBS EJD FDB HZ~ IXB KQ8 M41 M~E NCXOZ O-L O9- OK1 RIG ROL SSZ AAYWO AAYXX ACVFH ADCNI ADVLN AEUPX AFPUW AIGII AKBMS AKRWK AKYEP CITATION |
| ID | FETCH-LOGICAL-c352t-c14c06021ac66ffbddc2d562cc7441085b0f283c0baf9fd2db3ae5f8f30cfc313 |
| IEDL.DBID | IXB |
| ISSN | 2212-8271 |
| IngestDate | Thu Apr 24 22:56:22 EDT 2025 Tue Jul 01 02:31:25 EDT 2025 Wed May 17 00:08:32 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | deep learning manufacturing systems object detection supervised learning convolutional neural network |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c352t-c14c06021ac66ffbddc2d562cc7441085b0f283c0baf9fd2db3ae5f8f30cfc313 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S2212827121010714 |
| PageCount | 6 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_procir_2021_11_173 crossref_primary_10_1016_j_procir_2021_11_173 elsevier_sciencedirect_doi_10_1016_j_procir_2021_11_173 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021 2021-00-00 |
| PublicationDateYYYYMMDD | 2021-01-01 |
| PublicationDate_xml | – year: 2021 text: 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Procedia CIRP |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Hirano, Garcia, Sukthankar, Hoogs (bib00010) 2006 Huang, Zhang, Jiang (bib0007) 2008; 36 Zheng, wang, Sang, Zhong, Liu, Liu, Mubarok, Yu, Xu (bib0002) 2018; 13 Liu, Xu (bib0003) 2017; 63 Wang, Ma, Zhang, Gao, Wu (bib0005) 2018; 48 Tzutalin. LabelImg: Git code. Liukkonen, Tsai (bib0008) 2016; 87 VDI 4416 (bib0004) 2015 Accessed 3 March 2020. Tensorflow. TensorFlow Model Garden. Accessed 9 December 2020. Mourtzis, Milas, Athinaios (bib0001) 2018; 78 Jansen (bib0006) 1993 Riordan, Toal, Newe, Dooly (bib0009) 2019; 38 Zheng (10.1016/j.procir.2021.11.173_bib0002) 2018; 13 10.1016/j.procir.2021.11.173_bib00011 Hirano (10.1016/j.procir.2021.11.173_bib00010) 2006 Mourtzis (10.1016/j.procir.2021.11.173_bib0001) 2018; 78 10.1016/j.procir.2021.11.173_bib00012 Jansen (10.1016/j.procir.2021.11.173_bib0006) 1993 VDI 4416 (10.1016/j.procir.2021.11.173_bib0004) 2015 Riordan (10.1016/j.procir.2021.11.173_bib0009) 2019; 38 Wang (10.1016/j.procir.2021.11.173_bib0005) 2018; 48 Liukkonen (10.1016/j.procir.2021.11.173_bib0008) 2016; 87 Liu (10.1016/j.procir.2021.11.173_bib0003) 2017; 63 Huang (10.1016/j.procir.2021.11.173_bib0007) 2008; 36 |
| References_xml | – volume: 38 start-page: 408 year: 2019 end-page: 414 ident: bib0009 article-title: Object recognition within smart manufacturing publication-title: Procedia Manufacturing – year: 2015 ident: bib0004 publication-title: Production data acquisition and identification (germ: Betriebsdatenerfassung und-identifikation): Identification systems – volume: 87 start-page: 2509 year: 2016 end-page: 2531 ident: bib0008 article-title: Toward decentralized intelligence in manufacturing: recent trends in automatic identification of things publication-title: Int. J. Adv. Manuf. Technol. – year: 1993 ident: bib0006 publication-title: Rechnergestützte Betriebsorganisation: CA-Techniken in der Fertigung – reference: Tzutalin. LabelImg: Git code. – volume: 78 start-page: 301 year: 2018 end-page: 306 ident: bib0001 publication-title: Towards Machine Shop 4.0: A General Machine Model for CNC machine-tools through OPC-UA – volume: 63 start-page: 70 year: 2017 end-page: 75 ident: bib0003 article-title: Cyber-physical Machine Tool-The Era of Machine Tool 4.0 publication-title: CIRP Procedia – volume: 13 start-page: 137 year: 2018 end-page: 150 ident: bib0002 article-title: Smart manufacturing systems for Industry 4.0: Conceptual framework, scenarios, and future perspectives publication-title: Front. Mech. Eng. – volume: 36 start-page: 752 year: 2008 end-page: 764 ident: bib0007 article-title: RFID-based wireless manufacturing for real-time management of job shop WIP inventories publication-title: Int. J. Adv. Manuf. Technol. – volume: 48 start-page: 144 year: 2018 end-page: 156 ident: bib0005 publication-title: Deep learning for smart manufacturing: Methods and applications – reference: . Accessed 3 March 2020. – start-page: 49 year: 2006 end-page: 64 ident: bib00010 article-title: Industry and Object Recognition: Applications, Applied Research and Challenges publication-title: Toward Category-Level Object Recognition – reference: . Accessed 9 December 2020. – reference: Tensorflow. TensorFlow Model Garden. – start-page: 49 year: 2006 ident: 10.1016/j.procir.2021.11.173_bib00010 article-title: Industry and Object Recognition: Applications, Applied Research and Challenges – volume: 13 start-page: 137 year: 2018 ident: 10.1016/j.procir.2021.11.173_bib0002 article-title: Smart manufacturing systems for Industry 4.0: Conceptual framework, scenarios, and future perspectives publication-title: Front. Mech. Eng. doi: 10.1007/s11465-018-0499-5 – year: 2015 ident: 10.1016/j.procir.2021.11.173_bib0004 – volume: 87 start-page: 2509 year: 2016 ident: 10.1016/j.procir.2021.11.173_bib0008 article-title: Toward decentralized intelligence in manufacturing: recent trends in automatic identification of things publication-title: Int. J. Adv. Manuf. Technol. doi: 10.1007/s00170-016-8628-y – volume: 48 start-page: 144 year: 2018 ident: 10.1016/j.procir.2021.11.173_bib0005 publication-title: Deep learning for smart manufacturing: Methods and applications – volume: 36 start-page: 752 year: 2008 ident: 10.1016/j.procir.2021.11.173_bib0007 article-title: RFID-based wireless manufacturing for real-time management of job shop WIP inventories publication-title: Int. J. Adv. Manuf. Technol. doi: 10.1007/s00170-006-0897-4 – volume: 38 start-page: 408 year: 2019 ident: 10.1016/j.procir.2021.11.173_bib0009 article-title: Object recognition within smart manufacturing publication-title: Procedia Manufacturing doi: 10.1016/j.promfg.2020.01.052 – volume: 78 start-page: 301 year: 2018 ident: 10.1016/j.procir.2021.11.173_bib0001 publication-title: Towards Machine Shop 4.0: A General Machine Model for CNC machine-tools through OPC-UA – ident: 10.1016/j.procir.2021.11.173_bib00012 – year: 1993 ident: 10.1016/j.procir.2021.11.173_bib0006 – volume: 63 start-page: 70 year: 2017 ident: 10.1016/j.procir.2021.11.173_bib0003 article-title: Cyber-physical Machine Tool-The Era of Machine Tool 4.0 publication-title: CIRP Procedia doi: 10.1016/j.procir.2017.03.078 – ident: 10.1016/j.procir.2021.11.173_bib00011 |
| SSID | ssj0000740312 |
| Score | 2.138336 |
| Snippet | Manufacturing systems need to be highly adaptive and flexible to meet heterogeneous customer requirements and require fast and accurate object identification.... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 1029 |
| SubjectTerms | convolutional neural network deep learning manufacturing systems object detection supervised learning |
| Title | Object detection in factory based on deep learning approach |
| URI | https://dx.doi.org/10.1016/j.procir.2021.11.173 |
| Volume | 104 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEB5KvehBfGJ9lBy8xu5u0n3gqRZLsaigFntbspNEVmQtsh789072IRVEweOGDITZ8M2XZOYbgFNPDY30UPEEA8llYHyuEiu4FRJDpVWUxK52-PomnM7l1WK46MC4rYVxaZUN9teYXqF1MzJovDlY5vngPiDUjYPIKWD5rgyHcFjIuCriW1x83bNQiKR96x4T3HzuDNoKuirNy8WJ3AmDBj7Bx5kfiZ8j1ErUmWzBZkMX2ahe0TZ0TLEDGysigrtwfpu5uxSmTVmlVRUsL1jdRueDuSClGY1pY5asaRHxxFol8T2YTy4fxlPetETgSEyp5OhL9EJaq8IwtDbTGgNNFAYxIl5D9CnzLBEG9DJlE6sDnQllhja2wkOLwhf70C1eC3MALMwsKs8IQUdAKdDEmoJYFMU6lsqGRvZAtG5IsdELd20rXtI2Mew5rZ2XOufRUSIl5_WAf1kta72MP-ZHrYfTb_89JUj_1fLw35ZHsO6-6ouUY-iWb-_mhKhFmfVhbTS7e5z1qz30CcIIzo0 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3LSsNAFL3UulAX4hPrcxa6HJvMTJMUceGT1ra60EJ3cTIPqUgsWpF-lz_onSaRCqIgdDvJDcPJ5J4zk_sA2PdkzQhPSVpXTFDBjE9l3XJquVCB1DKsRy53uHMdNLriqlfrleCjyIVxYZW57898-thb5yPVHM3qoN-v3jL0uhELXQUs36Xh5JGVLTN6x33b63HzHF_yAWOXF3dnDZq3FqAKFceQKl8oL0B-kyoIrE20VkyjFFAqRH2AMiTxLBKv8hJp61YznXBpajay3FNWcZ_jc2dgFtVH6LxBs3f6dbCDnIwfivt74SZI3QyLlL1xXJkjpr6rRMp89FeHfsh_psQJmrtcgsVcn5KTDIJlKJl0BRYmqhauwtFN4g5viDbDcRxXSvopyfr2jIhjRU1wTBszIHlPigdSlC5fg-5UgFqHcvqcmg0gQWKV9AznuOcUXJlII2uGYaQjIW1gRAV4AUOs8gLlrk_GU1xEoj3GGXixAw_3LjGCVwH6ZTXICnT8cX9YIBx_W2gxcsivlpv_ttyDucZdpx23m9etLZh3V7JTnG0oD1_ezA7qmmGyO15HBO6nvXA_AWGSC-s |
| 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+in+factory+based+on+deep+learning+approach&rft.jtitle=Procedia+CIRP&rft.au=Yi%2C+Li&rft.au=Siedler%2C+Carina&rft.au=Kinkel%2C+Yann&rft.au=Glatt%2C+Moritz&rft.date=2021&rft.pub=Elsevier+B.V&rft.issn=2212-8271&rft.eissn=2212-8271&rft.volume=104&rft.spage=1029&rft.epage=1034&rft_id=info:doi/10.1016%2Fj.procir.2021.11.173&rft.externalDocID=S2212827121010714 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2212-8271&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2212-8271&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2212-8271&client=summon |