{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:42:53Z","timestamp":1774964573443,"version":"3.50.1"},"reference-count":13,"publisher":"Wiley","license":[{"start":{"date-parts":[[2018,6,14]],"date-time":"2018-06-14T00:00:00Z","timestamp":1528934400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key Program of High-speed Railway Basic Research Joint Fund of China Railway","award":["U1434211"],"award-info":[{"award-number":["U1434211"]}]},{"name":"Key Program of High-speed Railway Basic Research Joint Fund of China Railway","award":["2017G003-H"],"award-info":[{"award-number":["2017G003-H"]}]},{"name":"Science and Technology Development Program of China Railway","award":["U1434211"],"award-info":[{"award-number":["U1434211"]}]},{"name":"Science and Technology Development Program of China Railway","award":["2017G003-H"],"award-info":[{"award-number":["2017G003-H"]}]},{"DOI":"10.13039\/501100005195","name":"China University of Mining and Technology","doi-asserted-by":"publisher","award":["U1434211"],"award-info":[{"award-number":["U1434211"]}],"id":[{"id":"10.13039\/501100005195","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005195","name":"China University of Mining and Technology","doi-asserted-by":"publisher","award":["2017G003-H"],"award-info":[{"award-number":["2017G003-H"]}],"id":[{"id":"10.13039\/501100005195","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Scientific Programming"],"published-print":{"date-parts":[[2018,6,14]]},"abstract":"<jats:p>Railway subgrade defect is the serious threat to train safety. Vehicle-borne GPR method has become the main railway subgrade detection technology with its advantages of rapidness and nondestructiveness. However, due to the large amount of detection data and the variety in defect shape and size, defect recognition is a challenging task. In this work, the method based on deep learning is proposed to recognize defects from the ground penetrating radar (GPR) profile of subgrade detection data. Based on the Faster R-CNN framework, the improvement strategies of feature cascade, adversarial spatial dropout network (ASDN), Soft-NMS, and data augmentation have been integrated to improve recognition accuracy, according to the characteristics of subgrade defects. The experimental results indicates that compared with traditional SVM+HOG method and the baseline Faster R-CNN, the improved model can achieve better performance. The model robustness is demonstrated by a further comparison experiment of various defect types. In addition, the improvements to model performance of each improvement strategy are verified by an ablation experiment of improvement strategies. This paper tries to explore the new thinking for the application of deep learning method in the field of railway subgrade defect recognition.<\/jats:p>","DOI":"10.1155\/2018\/4832972","type":"journal-article","created":{"date-parts":[[2018,6,14]],"date-time":"2018-06-14T19:32:47Z","timestamp":1529004767000},"page":"1-12","source":"Crossref","is-referenced-by-count":71,"title":["Railway Subgrade Defect Automatic Recognition Method Based on Improved Faster R-CNN"],"prefix":"10.1155","volume":"2018","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-2547","authenticated-orcid":true,"given":"Xinjun","family":"Xu","sequence":"first","affiliation":[{"name":"School of Mechanical Electronic & Information Engineering, China University of Mining & Technology, Beijing 100083, China"},{"name":"Infrastructure Inspection Research Institute, China Academy of Railway Sciences, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9517-756X","authenticated-orcid":true,"given":"Yang","family":"Lei","sequence":"additional","affiliation":[{"name":"Infrastructure Inspection Research Institute, China Academy of Railway Sciences, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5732-6197","authenticated-orcid":true,"given":"Feng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Mechanical Electronic & Information Engineering, China University of Mining & Technology, Beijing 100083, China"}]}],"member":"311","reference":[{"issue":"6","key":"3","first-page":"102","volume":"42","year":"2009","journal-title":"China Civil Engineering Journal"},{"issue":"3","key":"4","first-page":"142","volume":"32","year":"2010","journal-title":"Journal of the China Railway Society"},{"issue":"6","key":"5","first-page":"2302","volume":"24","year":"2009","journal-title":"Progress in Geophysics"},{"issue":"11","key":"6","first-page":"138","volume":"46","year":"2013","journal-title":"China Civil Engineering Journal"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.10.002"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2568758"},{"issue":"6","key":"16","first-page":"1283","volume":"12","year":"2015","journal-title":"Journal of Railway Science and Engineering"},{"issue":"12","key":"20","first-page":"183","volume":"58","year":"2005","journal-title":"Encyclopedia of RF and Microwave Engineering"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"container-title":["Scientific Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2018\/4832972.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2018\/4832972.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2018\/4832972.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,6,14]],"date-time":"2018-06-14T19:32:57Z","timestamp":1529004777000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/sp\/2018\/4832972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,14]]},"references-count":13,"alternative-id":["4832972","4832972"],"URL":"https:\/\/doi.org\/10.1155\/2018\/4832972","relation":{},"ISSN":["1058-9244","1875-919X"],"issn-type":[{"value":"1058-9244","type":"print"},{"value":"1875-919X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,14]]}}}