An Efficient Multiresolution Network for Vehicle Reidentification | |
Shen, Fei6; Zhu, Jianqing6; Zhu, Xiaobin5; Huang, Jingchang4; Zeng, Huanqiang6; Lei, Zhen1,2,3; Cai, Canhui6 | |
刊名 | IEEE INTERNET OF THINGS JOURNAL |
2022-06-01 | |
卷号 | 9期号:11页码:9049-9059 |
关键词 | Image resolution Training Feature extraction Spatial resolution Proposals Internet of Things Deep learning Deep learning image representation multiresolution vehicle reidentification |
ISSN号 | 2327-4662 |
DOI | 10.1109/JIOT.2021.3119525 |
通讯作者 | Zhu, Jianqing(jqzhu@hqu.edu.cn) ; Zeng, Huanqiang(zeng0043@hqu.edu.cn) |
英文摘要 | In general, vehicle images have varying resolutions due to vehicles' movements and different camera settings. However, most existing vehicle reidentification models are single-resolution deep networks trained with preuniformly resizing vehicle images, which underestimate adverse effects of varying resolutions and lead to unsatisfactory performance. A straightforward solution for dealing with varying resolutions is to train multiple vehicle reidentification models. Each model is independently trained with images of a specific resolution. However, this straightforward solution requires significant overhead and ignores intrinsic associations among different resolution images. For that, an efficient multiresolution network (EMRN) is proposed for vehicle reidentification in this article. First, EMRN embeds a newly designed multiresolution feature dimension uniform module (MR-FDUM) behind a traditional backbone network (i.e., ResNet-50). As a result, the whole model can extract fixed dimensional features from different resolution images so that it can be trained with one loss function of fixed dimensional parameters rather than training multiple models. Second, a multiresolution image randomly feeding strategy is designed to train EMRN, making each minibatch data of a random resolution during the training process. Consequently, EMRN can implicitly learn collaborative multiresolution features via only a unitary deep network. The experiments on three large-scale data sets, i.e., VeRi776, VehicleID, and VRIC, demonstrate that EMRN is superior to state-of-the-art vehicle reidentification methods. |
资助项目 | National Key Research and Development Program[2020YFC2003901] ; National Natural Science Foundation of China[61976098] ; National Natural Science Foundation of China[61871434] ; National Natural Science Foundation of China[61802136] ; National Natural Science Foundation of China[6217070593] ; Natural Science Foundation for Outstanding Young Scholars of Fujian Province[2019J06017] ; Key Science and Technology Project of Xiamen City[3502ZCQ20191005] ; Science and Technology Bureau of Quanzhou[2018C115R] ; Postgraduates' Innovative Fund in Scientific Research of Huaqiao University[18014084008] |
WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000800215600092 |
资助机构 | National Key Research and Development Program ; National Natural Science Foundation of China ; Natural Science Foundation for Outstanding Young Scholars of Fujian Province ; Key Science and Technology Project of Xiamen City ; Science and Technology Bureau of Quanzhou ; Postgraduates' Innovative Fund in Scientific Research of Huaqiao University |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/49566] |
专题 | 自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心 |
通讯作者 | Zhu, Jianqing; Zeng, Huanqiang |
作者单位 | 1.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, Hong Kong Inst Sci & Innovat, Hong Kong, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Biometr & Secur Res, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Shanghai 200050, Peoples R China 5.Univ Sci & Technol Beijing, Dept Comp Sci & Technol, Beijing 100083, Peoples R China 6.Huaqiao Univ, Coll Engn, Quanzhou 362021, Peoples R China |
推荐引用方式 GB/T 7714 | Shen, Fei,Zhu, Jianqing,Zhu, Xiaobin,et al. An Efficient Multiresolution Network for Vehicle Reidentification[J]. IEEE INTERNET OF THINGS JOURNAL,2022,9(11):9049-9059. |
APA | Shen, Fei.,Zhu, Jianqing.,Zhu, Xiaobin.,Huang, Jingchang.,Zeng, Huanqiang.,...&Cai, Canhui.(2022).An Efficient Multiresolution Network for Vehicle Reidentification.IEEE INTERNET OF THINGS JOURNAL,9(11),9049-9059. |
MLA | Shen, Fei,et al."An Efficient Multiresolution Network for Vehicle Reidentification".IEEE INTERNET OF THINGS JOURNAL 9.11(2022):9049-9059. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论