{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:35:17Z","timestamp":1780587317215,"version":"3.54.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61533019"],"award-info":[{"award-number":["61533019"]}],"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":["91720000"],"award-info":[{"award-number":["91720000"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/tvt.2018.2843394","type":"journal-article","created":{"date-parts":[[2018,6,4]],"date-time":"2018-06-04T22:43:05Z","timestamp":1528152185000},"page":"8019-8030","source":"Crossref","is-referenced-by-count":74,"title":["MFR-CNN: Incorporating Multi-Scale Features and Global Information for Traffic Object Detection"],"prefix":"10.1109","volume":"67","author":[{"given":"Hui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2744-1191","authenticated-orcid":false,"given":"Kunfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonglin","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Gou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9185-3989","authenticated-orcid":false,"given":"Fei-Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","first-page":"577","article-title":"Parallel Imaging: A new theoretical framework for image generation","volume":"30","author":"wang","year":"2017","journal-title":"Pattern Recognit Artif Intell"},{"key":"ref39","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"szegedy","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref38","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","first-page":"66","article-title":"Vehicle detection combining gradient\n analysis and adaboost classification","author":"khammari","year":"0","journal-title":"Proc IEEE Intell Transp Syst"},{"key":"ref32","first-page":"951","article-title":"Vehicle detection, tracking and classification in urban traffic","author":"chen","year":"0","journal-title":"Proc Int IEEE Conf Intell Transp Syst"},{"key":"ref31","first-page":"480","article-title":"Nighttime\n vehicle detection using deformable parts model","volume":"2","author":"chen","year":"0","journal-title":"Proc 7th Int Conf Intell Human–Mach Syst Cybern"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2012.2187894"},{"key":"ref37","first-page":"1","article-title":"Going deeper with convolutions","author":"szegedy","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref36","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0968-090X(95)00009-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0968-090X(93)90025-B"},{"key":"ref60","first-page":"886","article-title":"Histograms of oriented gradients for human detection","volume":"1","author":"dalal","year":"0","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref62","first-page":"424","article-title":"Local\n decorrelation for improved pedestrian detection","author":"nam","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300479"},{"key":"ref63","first-page":"1751","article-title":"Filtered\n channel features for pedestrian detection","author":"zhang","year":"0","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref64","first-page":"1904","article-title":"Deep learning strong parts for pedestrian\n detection","author":"tian","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref27","first-page":"22","article-title":"Moving target classification based on shape\n features from real-time video","volume":"8","author":"beiping","year":"2010","journal-title":"Chin J Sci Instrum"},{"key":"ref65","first-page":"3361","article-title":"Learning\n complexity-aware cascades for deep pedestrian detection","author":"cai","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2474388"},{"key":"ref29","first-page":"766","article-title":"Vehicle detection using discriminatively\n trained part templates with variable size","author":"niknejad","year":"0","journal-title":"Proc IEEE Intell Veh Symp"},{"key":"ref67","first-page":"265","article-title":"Tensorflow: A system for large-scale machine\n learning","volume":"16","author":"abadi","year":"0","journal-title":"Proc USENIX Conf Oper Syst Des Implementation"},{"key":"ref68","first-page":"1490","article-title":"Parallel\n vision: An ACP-based approach to intelligent vision computing","volume":"42","author":"wang","year":"2016","journal-title":"Acta Autom Sin"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9569-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2003.821213"},{"key":"ref1","article-title":"Traffic surveillance and detection technology development: new traffic sensor technology final\n report","author":"malik","year":"1997","journal-title":"California Partners for Advanced Transit and Highways (PATH)"},{"key":"ref20","first-page":"1440","article-title":"Fast R-CNN","author":"girshick","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref22","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref24","first-page":"240","article-title":"A novel method for people and vehicle classification\n based on hough line feature","author":"xu","year":"0","journal-title":"Proc Int Conf Inf Sci Technol"},{"key":"ref23","first-page":"133","article-title":"A two-stage approach to people and vehicle detection with HOG-based SVM","author":"han","year":"0","journal-title":"Proc Performance Metrics Intell Syst Workshop"},{"key":"ref26","first-page":"429","article-title":"Classification of moving targets based on motion and appearance","author":"bogomolov","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2002.1048032"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref58","first-page":"340","article-title":"Diagnosing error in object detectors","author":"hoiem","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465908"},{"key":"ref55","first-page":"424","article-title":"3D object proposals for accurate object class\n detection","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref52","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2488287"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2012.100"},{"key":"ref40","first-page":"12","article-title":"Inception-v4,\n inception-resnet and the impact of residual connections on learning","volume":"4","author":"szegedy","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref12","first-page":"278","article-title":"DAVE: A unified framework for fast\n vehicle detection and annotation","author":"zhou","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2158001"},{"key":"ref14","first-page":"i?511","article-title":"Rapid object detection using a boosted cascade of simple features","volume":"1","author":"viola","year":"0","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2170666"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/782432"},{"key":"ref17","first-page":"1097","article-title":"Imagenet\n classification with deep convolutional neural networks","author":"krizhevsky","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013","journal-title":"arXiv 1312 6229"},{"key":"ref19","first-page":"580","article-title":"Rich feature hierarchies for accurate\n object detection and semantic segmentation","author":"girshick","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2409889"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2331259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2509465"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2060218"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001415550150"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2812880"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2496545"},{"key":"ref46","first-page":"354","article-title":"A unified multi-scale deep convolutional\n neural network for fast object detection","author":"cai","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001416550041"},{"key":"ref47","first-page":"447","article-title":"Hypercolumns for object segmentation and\n fine-grained localization","author":"hariharan","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref41","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref44","first-page":"2874","article-title":"Inside-outside net: Detecting objects\n in context with skip pooling and recurrent neural networks","author":"bell","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref43","first-page":"3431","article-title":"Fully\n convolutional networks for semantic segmentation","author":"long","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/8466982\/08371213.pdf?arnumber=8371213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T09:20:36Z","timestamp":1643188836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8371213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":70,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2018.2843394","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9]]}}}