VRSDNet: vehicle re-identification with a shortly and densely connected convolutional neural network

被引:0
作者
Jianqing Zhu
Yongzhao Du
Yang Hu
Lixin Zheng
Canhui Cai
机构
[1] Huaqiao University,College of Engineering
[2] First Research Institute of the Ministry of Public Security of People’s Republic of China,undefined
来源
Multimedia Tools and Applications | 2019年 / 78卷
关键词
Vehicle re-identification; Convolutional neural network; Deep learning;
D O I
暂无
中图分类号
学科分类号
摘要
Vehicle re-identification aiming to match vehicle images captured by different cameras plays an important role in video surveillance for public security. In this paper, we solve Vehicle Re-identification with a Shortly and Densely connected convolutional neural Network (VRSDNet). The proposed VRSDNet mainly consists of a list of short and dense units (SDUs), necessary pooling and spatial normalization layers. Specifically, each SDU contains a short list of densely connected convolutional layers and each convolutional layer is of the same appropriate channels. As a result, the number of connections and the input channel of each convolutional layer are restricted in each SDU, and the architecture of VRSDNet is simple. Extensive experiments on both VeRi and VehicleID datasets show that the proposed VRSDNet is obviously superior to multiple state-of-the-art vehicle re-identification methods in terms of accuracy and speed.
引用
收藏
页码:29043 / 29057
页数:14
相关论文
共 50 条
[21]   Joint Pyramid Feature Representation Network for Vehicle Re-identification [J].
Xiangwei Lin ;
Huanqiang Zeng ;
Jinhui Hou ;
Jiuwen Cao ;
Jianqing Zhu ;
Jing Chen .
Mobile Networks and Applications, 2020, 25 :1781-1792
[22]   Joint Pyramid Feature Representation Network for Vehicle Re-identification [J].
Lin, Xiangwei ;
Zeng, Huanqiang ;
Hou, Jinhui ;
Cao, Jiuwen ;
Zhu, Jianqing ;
Chen, Jing .
MOBILE NETWORKS & APPLICATIONS, 2020, 25 (05) :1781-1792
[23]   A Vehicle Comparison and Re-Identification System Based on Residual Network [J].
Yin, Weifeng ;
Min, Yusong ;
Zhai, Junyong .
MACHINES, 2022, 10 (09)
[24]   Person Re-identification for 365-day Video Surveillance Based on Stride Convolutional Neural Network [J].
Wang, Shengke ;
Zhang, Xiaoyan ;
Li, Rui ;
Zhu, Jianlin ;
Xue, Fenghui ;
Dong, Junyu .
TENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2018), 2019, 11069
[25]   Person Re-identification Based on Multi-information Flow Convolutional Neural Network [J].
Sang H.-F. ;
Wang C.-Z. ;
Lü Y.-Y. ;
He D.-K. ;
Liu Q. .
Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2019, 47 (02) :351-357
[26]   Dense 3D-Convolutional Neural Network for Person Re-Identification in Videos [J].
Liu, Jiawei ;
Zha, Zheng-Jun ;
Chen, Xuejin ;
Wang, Zilei ;
Zhang, Yongdong .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2019, 15 (01)
[27]   Dual attention granularity network for vehicle re-identification [J].
Jianhua Zhang ;
Jingbo Chen ;
Jiewei Cao ;
Ruyu Liu ;
Linjie Bian ;
Shengyong Chen .
Neural Computing and Applications, 2022, 34 :2953-2964
[28]   Global reference attention network for vehicle re-identification [J].
Gangwu Jiang ;
Xiyu Pang ;
Xin Tian ;
Yanli Zheng ;
Qinlan Meng .
Applied Intelligence, 2023, 53 :11328-11343
[29]   Heterogeneous context interaction network for vehicle re-identification [J].
Sun, Ke ;
Pang, Xiyu ;
Zheng, Meifeng ;
Nie, Xiushan ;
Li, Xi ;
Zhou, Houren ;
Yin, Yilong .
NEURAL NETWORKS, 2024, 169 :293-306
[30]   Dual attention granularity network for vehicle re-identification [J].
Zhang, Jianhua ;
Chen, Jingbo ;
Cao, Jiewei ;
Liu, Ruyu ;
Bian, Linjie ;
Chen, Shengyong .
NEURAL COMPUTING & APPLICATIONS, 2022, 34 (04) :2953-2964