{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T04:46:39Z","timestamp":1766983599280,"version":"3.37.3"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T00:00:00Z","timestamp":1613692800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T00:00:00Z","timestamp":1613692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2022,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This article mainly focuses on the most common types of high-speed railways malfunctions in overhead contact systems, namely, unstressed droppers, foreign-body invasions, and pole number-plate malfunctions, to establish a deep-network detection model. By fusing the feature maps of the shallow and deep layers in the pretraining network, global and local features of the malfunction area are combined to enhance the network's ability of identifying small objects. Further, in order to share the fully connected layers of the pretraining network and reduce the complexity of the model, Tucker tensor decomposition is used to extract features from the fused-feature map. The operation greatly reduces training time. Through the detection of images collected on the Lanxin railway line, experiments result show that the proposed multiview Faster R-CNN based on tensor decomposition had lower miss probability and higher detection accuracy for the three types faults. Compared with object-detection methods YOLOv3, SSD, and the original Faster R-CNN, the average miss probability of the improved Faster R-CNN model in this paper is decreased by 37.83%, 51.27%, and 43.79%, respectively, and average detection accuracy is increased by 3.6%, 9.75%, and 5.9%, respectively.<\/jats:p>","DOI":"10.1007\/s00371-021-02080-y","type":"journal-article","created":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T20:38:33Z","timestamp":1613767113000},"page":"1457-1467","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Multiview deep learning based on tensor decomposition and its application in fault detection of overhead contact systems"],"prefix":"10.1007","volume":"38","author":[{"given":"Xuewu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yansheng","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0362-8728","authenticated-orcid":false,"given":"Wenfeng","family":"Jing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,19]]},"reference":[{"key":"2080_CR1","first-page":"24","volume":"06","author":"G-K Yuan","year":"2016","unstructured":"Yuan, G.-K., Li, K.-Q.: Supporting economic and social upgrading development with the construction of railway transportation artery. China Emerg. Manag. 06, 24 (2016)","journal-title":"China Emerg. Manag."},{"key":"2080_CR2","first-page":"182","volume":"02","author":"C-H Li","year":"2012","unstructured":"Li, C.-H.: Talking about common fault points of catenary and technical measures to improve performance. Guide Sci-tech Mag. 02, 182 (2012)","journal-title":"Guide Sci-tech Mag."},{"issue":"2","key":"2080_CR3","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1109\/TII.2016.2628042","volume":"13","author":"E Karakose","year":"2017","unstructured":"Karakose, E., Gencoglu, M., Karak\u00f6se, M., Aydin, I., Akin, E.: A new experimental approach using image processing-based tracking for an efficient fault diagnosis in pantograph\u2013catenary systems. IEEE Trans. Ind. Informat. 13(2), 635\u2013643 (2017)","journal-title":"IEEE Trans. Ind. Informat."},{"key":"2080_CR4","doi-asserted-by":"publisher","first-page":"17049","DOI":"10.1109\/ACCESS.2020.2967831","volume":"8","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Liu, W., Nunez, A., Han, Z.: Unified deep learning architecture for the detection of all catenary support components. IEEE Access 8, 17049\u201317059 (2020)","journal-title":"IEEE Access"},{"key":"2080_CR5","doi-asserted-by":"publisher","first-page":"23210","DOI":"10.1109\/ACCESS.2019.2899074","volume":"7","author":"Z Qu","year":"2019","unstructured":"Qu, Z., Yuan, S., Chi, R., Chang, L., Zhao, L.: Genetic optimization method of pantograph and catenary comprehensive monitor status prediction model based on adadelta deep neural network. IEEE Access 7, 23210\u201323221 (2019)","journal-title":"IEEE Access"},{"issue":"8","key":"2080_CR6","doi-asserted-by":"publisher","first-page":"2849","DOI":"10.1109\/TIM.2018.2871353","volume":"68","author":"J Zhong","year":"2019","unstructured":"Zhong, J., HanLiu, Z., Han, Y., Zhang, W.: A CNN-based defect inspection method for catenary split pins in high-speed railway. IEEE Trans. Instrum. Meas. 68(8), 2849\u20132860 (2019)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2080_CR7","volume-title":"Generative adversarial networks based on dual discriminator and its application in OCS nest detection [D]","author":"P Yang","year":"2018","unstructured":"Yang, P.: Generative adversarial networks based on dual discriminator and its application in OCS nest detection [D]. Southwest Jiaotong University, Chengdu (2018)"},{"key":"2080_CR8","first-page":"225","volume":"5524","author":"C Petitjean","year":"2009","unstructured":"Petitjean, C., Heutte, L., Kouadio, R., et al.: A top-down approach for automatic dropper extraction in catenary scenes. Proc IbPRIA P\u00f3voa de Varzim Portugal 5524, 225\u2013232 (2009)","journal-title":"Proc IbPRIA P\u00f3voa de Varzim Portugal"},{"issue":"22","key":"2080_CR9","first-page":"250","volume":"55","author":"X-L Jiang","year":"2019","unstructured":"Jiang, X.-L., Jia, W.-B.: Machine vision detection method for foreign object intrusion in high- speed rail contact net. Comput. Eng. Appl. 55(22), 250\u2013257 (2019)","journal-title":"Comput. Eng. Appl."},{"key":"2080_CR10","unstructured":"Redmon J, Farhadi A 2018 YOLOv3: An Incremental Improvement"},{"issue":"10","key":"2080_CR11","first-page":"193","volume":"55","author":"J-F Wu","year":"2019","unstructured":"Wu, J.-F., Jin, W.-D., Tang, P.: Catenary pillar image anomaly detection combined with SVDD and CNN. Comput. Eng. Appl. 55(10), 193\u2013198 (2019)","journal-title":"Comput. Eng. Appl."},{"key":"2080_CR12","volume-title":"Application of image processing in detecting defects of catenary hanger","author":"Y-B Xu","year":"2018","unstructured":"Xu, Y.-B.: Application of image processing in detecting defects of catenary hanger. Southwest Jiaotong University, Chengdu (2018)"},{"key":"2080_CR13","doi-asserted-by":"publisher","first-page":"105622","DOI":"10.1109\/ACCESS.2020.3000506","volume":"8","author":"Q-F Guo","year":"2020","unstructured":"Guo, Q.-F., Liu, L., Xu, W.-J., et al.: An improved faster R-CNN for high-speed railway dropper detection. IEEE Access 8, 105622\u2013105633 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3000506","journal-title":"IEEE Access"},{"issue":"3","key":"2080_CR14","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/BF02310791","volume":"35","author":"D Carroll","year":"1970","unstructured":"Carroll, D., Chang, H.J.: Analysis of individual differences in multidimensional scaling via an n-way generalization of Eckart-Young decomposition. Psychometrika 35(3), 283\u2013319 (1970)","journal-title":"Psychometrika"},{"issue":"1","key":"2080_CR15","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/0167-9473(94)90132-5","volume":"18","author":"RA Harshman","year":"1994","unstructured":"Harshman, R.A., Lundy, M.E.: Parafac: Parallel factor analysis. Comput. Stat. Data Anal. 18(1), 39\u201372 (1994)","journal-title":"Comput. Stat. Data Anal."},{"issue":"3","key":"2080_CR16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF02289464","volume":"31","author":"LR Tucker","year":"1966","unstructured":"Tucker, L.R.: Some mathematical notes on three-mode factor analysis. Psychometrika 31(3), 279\u2013311 (1966)","journal-title":"Psychometrika"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02080-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02080-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02080-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T14:16:59Z","timestamp":1658413019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02080-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,19]]},"references-count":16,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["2080"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02080-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2021,2,19]]},"assertion":[{"value":"3 February 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}