{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T22:13:20Z","timestamp":1761948800831,"version":"3.40.5"},"reference-count":26,"publisher":"Wiley","license":[{"start":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T00:00:00Z","timestamp":1655424000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Zhejiang Provincial Key Lab of Equipment Electronics","award":["2022C01062"],"award-info":[{"award-number":["2022C01062"]}]},{"name":"Zhejiang Provincial Major Research and Development Project of China","award":["2022C01062"],"award-info":[{"award-number":["2022C01062"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Sensors"],"published-print":{"date-parts":[[2022,6,17]]},"abstract":"In recent years, vehicle type detection has had an important role in traffic management. A lightweight detection network based on multiscale ghost convolution called G-YOLOX is designed in this paper. It is suitable for practical applications for an embedded device. Specifically, \n \n 3<\/a:mn>\n \u00d7<\/a:mo>\n 3<\/a:mn>\n <\/a:math>\n <\/jats:inline-formula> convolutions and \n \n 5<\/c:mn>\n \u00d7<\/c:mo>\n 5<\/c:mn>\n <\/c:math>\n <\/jats:inline-formula> and \n \n 7<\/e:mn>\n \u00d7<\/e:mo>\n 7<\/e:mn>\n <\/e:math>\n <\/jats:inline-formula> ghost convolutions are combined to fully utilize different feature information. A series of linear transformations was designed to generate ghost feature maps to ensure that the network is lightweight. Moreover, a dataset of images showing different vehicles in a city environment was established. Altogether, 20,000 road scene images were collected, and seven categories of vehicles were identified. Extensive experiments with the benchmark datasets VOC2007 and VOC2012 and with our dataset demonstrate the superiority of the proposed G-YOLOX over the original YOLOX. The proposed G-YOLOX can achieve a nearly invariable mean average precision of 0.5, while the size of the weight file decreased by 40% and the number of parameters decreased by 67% compared to the original YOLOX network.<\/jats:p>","DOI":"10.1155\/2022\/4488400","type":"journal-article","created":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T21:35:20Z","timestamp":1655501720000},"page":"1-10","source":"Crossref","is-referenced-by-count":7,"title":["G-YOLOX: A Lightweight Network for Detecting Vehicle Types"],"prefix":"10.1155","volume":"2022","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6023-2434","authenticated-orcid":true,"given":"Qiang","family":"Luo","sequence":"first","affiliation":[{"name":"School of Electronics and Information, Hangzhou Dianzi University, Hangzhou, China"},{"name":"School of Communication and Electronics, Jiangxi Science and Technology Normal University, Nanchang, China"},{"name":"Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, China"}]},{"given":"Junfan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Hangzhou Dianzi University, Hangzhou, China"},{"name":"Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5930-9526","authenticated-orcid":true,"given":"Mingyu","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Hangzhou Dianzi University, Hangzhou, China"},{"name":"Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, China"}]},{"given":"Huipin","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Hangzhou Dianzi University, Hangzhou, China"},{"name":"Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, China"}]},{"given":"Hongtao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang LEAPMOTOR Technology Co., Ltd, China"}]},{"given":"Qiheng","family":"Miao","sequence":"additional","affiliation":[{"name":"Zhejiang Huaruijie Technology Co., Ltd, China"}]}],"member":"311","reference":[{"first-page":"10076","article-title":"Exploring self-attention for image recognition","author":"H. Zhao","key":"1"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05978-9"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.03.037"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksues.2020.06.001"},{"first-page":"1492","article-title":"Aggregated residual transformations for deep neural networks","author":"S. Xie","key":"5"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103514"},{"first-page":"2961","article-title":"Mask r-cnn","author":"K. He","key":"7"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"K. Simonyan","key":"8"},{"key":"9","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","volume":"28","author":"S. Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"T. Y. Lin","key":"10"},{"issue":"3","key":"11","first-page":"5308","article-title":"An optimized deep learning model for flower classification using NAS-FPN and faster R-CNN","volume":"9","author":"I. Patel","year":"2020","journal-title":"International Journal of Scientific & Technology Research"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.3390\/app10217751"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.04.283"},{"first-page":"1580","article-title":"Ghostnet: more features from cheap operations","author":"K. Han","key":"14"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.3390\/s19173787"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.3390\/pr8050595"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0264551"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105326"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.01.016"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9030537"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2021.102908"},{"article-title":"YOLOv5","year":"2021","author":"G. Jocher","key":"22"},{"article-title":"YOLOX: exceeding YOLO series in 2021","year":"2021","author":"Z. Ge","key":"23"},{"first-page":"2636","article-title":"Bdd100k: a diverse driving dataset for heterogeneous multitask learning","author":"F. Yu","key":"24"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102907"},{"first-page":"6848","article-title":"Shufflenet: an extremely efficient convolutional neural network for mobile devices","author":"X. Zhang","key":"26"}],"container-title":["Journal of Sensors"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/4488400.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/4488400.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/4488400.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T21:35:31Z","timestamp":1655501731000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/js\/2022\/4488400\/"}},"subtitle":[],"editor":[{"given":"Yuxing","family":"Li","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,6,17]]},"references-count":26,"alternative-id":["4488400","4488400"],"URL":"https:\/\/doi.org\/10.1155\/2022\/4488400","relation":{},"ISSN":["1687-7268","1687-725X"],"issn-type":[{"type":"electronic","value":"1687-7268"},{"type":"print","value":"1687-725X"}],"subject":[],"published":{"date-parts":[[2022,6,17]]}}}