{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:30:17Z","timestamp":1773156617801,"version":"3.50.1"},"reference-count":41,"publisher":"Wiley","license":[{"start":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T00:00:00Z","timestamp":1660608000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Program of Sichuan","award":["2021YJ0080"],"award-info":[{"award-number":["2021YJ0080"]}]},{"name":"Science and Technology Program of Sichuan","award":["61771409"],"award-info":[{"award-number":["61771409"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2021YJ0080"],"award-info":[{"award-number":["2021YJ0080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771409"],"award-info":[{"award-number":["61771409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Sensors"],"published-print":{"date-parts":[[2022,8,16]]},"abstract":"<jats:p>This paper proposed a novel anomaly detection (AD) approach of high-speed train images based on convolutional neural networks and the Vision Transformer. Different from previous AD works, in which anomalies are identified with a single image using classification, segmentation, or object detection methods, the proposed method detects abnormal difference between two images taken at different times of the same region. In other words, we cast anomaly detection problem with a single image into a difference detection problem with two images. The core idea of the proposed method is that the \u201canomaly\u201d commonly represents an abnormal state instead of a specific object, and this state should be identified by a pair of images. In addition, we introduced a deep feature difference AD network (AnoDFDNet) which sufficiently explored the potential of the Vision Transformer and convolutional neural networks. To verify the effectiveness of the proposed AnoDFDNet, we gathered three datasets, a difference dataset (Diff dataset), a foreign body dataset (FB dataset), and an oil leakage dataset (OL dataset). Experimental results on the above datasets demonstrate the superiority of the proposed method. In terms of the F1-score, the AnoDFDNet obtained 76.24%, 81.04%, and 83.92% on Diff dataset, FB dataset, and OL dataset, respectively.<\/jats:p>","DOI":"10.1155\/2022\/3538541","type":"journal-article","created":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T02:35:26Z","timestamp":1660703726000},"page":"1-14","source":"Crossref","is-referenced-by-count":19,"title":["AnoDFDNet: A Deep Feature Difference Network for Anomaly Detection"],"prefix":"10.1155","volume":"2022","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6912-742X","authenticated-orcid":true,"given":"Zhixue","family":"Wang","sequence":"first","affiliation":[{"name":"School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7140-5414","authenticated-orcid":true,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3152-7863","authenticated-orcid":true,"given":"Lin","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8321-7074","authenticated-orcid":true,"given":"Nan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","article-title":"Deep learning for anomaly detection: a survey","author":"C. Raghavendra","year":"2019"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3052449"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.04.007"},{"key":"5","first-page":"23","article-title":"Real-time illegal parking detection system based on deep learning","author":"X. M. Xie"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging4020036"},{"key":"7","first-page":"146","article-title":"Unsupervised anomaly detection with generative adversarial networks to guide marker discovery","author":"T. Schlegl"},{"key":"8","first-page":"622","article-title":"GANomaly: semi-supervised anomaly detection via adversarial training","author":"A. Samet"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.10.018"},{"key":"10","first-page":"384","article-title":"Potential fault region detection in TFDS images based on convolutional neural network","volume":"10157","author":"J. H. Sun","year":"2016","journal-title":"Infrared Technology and Applications, and Robot Sensing and Advanced Control"},{"key":"11","first-page":"14897","article-title":"Multiresolution knowledge distillation for anomaly detection","author":"M. Salehi"},{"key":"12","first-page":"4182","article-title":"Uninformed students: student-teacher anomaly detection with discriminative latent embeddings","author":"B. Paul"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2004.01.008"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.893278"},{"key":"15","first-page":"2333","article-title":"A GPU-based vision system for real time detection of fastening elements in railway inspection","author":"P. De Ruvo"},{"issue":"8","key":"16","doi-asserted-by":"crossref","first-page":"2835","DOI":"10.1109\/TIM.2011.2119110","article-title":"Automated inspection system for rolling stock brake shoes","volume":"60","author":"K. HyunCheo","year":"2011","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2015.2479101"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2017.2775345"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2019.2915404"},{"issue":"10","key":"20","first-page":"1906","article-title":"Pandrol track fastener defect detection based on local convolutional neural networks","volume":"235","author":"A. Q. Ma","year":"2020","journal-title":"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.01.008"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2013.2283741"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3117357"},{"issue":"5","key":"24","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1080\/23248378.2020.1825128","article-title":"Convolutional neural network for detecting railway fastener defects using a developed 3D laser system","volume":"9","author":"Y. Zhan","year":"2021","journal-title":"International Journal of Rail Transportation"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5554920"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3151165"},{"key":"27","first-page":"76","article-title":"Defect detection in high-speed railway overhead contact system: importance, challenges, and methods","author":"L. Yao"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04337-z"},{"key":"29","first-page":"621","article-title":"Material classification and semantic segmentation of railway track images with deep convolutional neural networks","author":"X. Giben"},{"key":"30","first-page":"192","article-title":"Bolt detection of key component for high-speed trains based on deep learning","author":"Z. X. Wang"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3083561"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3033726"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/8956164"},{"key":"34","doi-asserted-by":"crossref","DOI":"10.1155\/2022\/3538541","article-title":"AnoDFDNet: a deep feature difference network for anomaly detection","author":"Z. Wang","year":"2022"},{"key":"35","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"A. Dosovitskiy"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1364\/OE.440720"},{"key":"37","first-page":"6881","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"S. Zheng"},{"key":"38","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"O. Ronneberger"},{"key":"39","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"L. C. Chen","year":"2019"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.059"},{"key":"41","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"L. V. D. Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"container-title":["Journal of Sensors"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/3538541.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/3538541.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/3538541.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T00:55:20Z","timestamp":1676422520000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/js\/2022\/3538541\/"}},"subtitle":[],"editor":[{"given":"Sangsoon","family":"Lim","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,8,16]]},"references-count":41,"alternative-id":["3538541","3538541"],"URL":"https:\/\/doi.org\/10.1155\/2022\/3538541","relation":{},"ISSN":["1687-7268","1687-725X"],"issn-type":[{"value":"1687-7268","type":"electronic"},{"value":"1687-725X","type":"print"}],"subject":[],"published":{"date-parts":[[2022,8,16]]}}}