帮助 关于我们

返回检索结果

基于部件融合特征的车辆重识别算法
Vehicle Re-identification Algorithm Based on Component Fusion Feature

查看参考文献15篇

李熙莹 1,2,3,4   周智豪 1,2,3,4   邱铭凯 1,2,3,4  
文摘 针对车辆型号相同但车辆个体不同的重识别问题,提出一种新的车辆重识别算法。运用部件检测算法获取不同车辆之间差异较大的车窗和车脸区域,对检测到的车窗和车脸区域进行特征提取并进行融合,生成新的融合特征,计算图像特征之间距离度量进行分类识别。在中山大学公开数据集VRID-1上进行测试,结果表明,该算法的Rank1匹配率达到66.67%,明显优于经典的传统特征表征算法,从而验证该算法是可行且有效的。
其他语种文摘 To address the re-identification problem of different individual vehicles with identical types,a new vehicle reidentification algorithm is proposed.According to the component detection algorithm,the window and the vehicle face region with large differences between different vehicles are obtained,and the vehicle features of the detected vehicle window and the vehicle face region are extracted and merged to generate new fusion features.The distance measurement between image features is calculated for classification and recognition.The test is carried out on the public dataset VRID-1 of Sun Yat-sen university and results show that the Rank1 matching rate of the algorithm reaches 66.67%,which is obviously better than the classical traditional feature representation algorithm,thus verifies the feasibility and validity of the algorithm.
来源 计算机工程 ,2019,45(6):12-20 【扩展库】
DOI 10.19678/j.issn.1000-3428.0052284
关键词 车辆重识别 ; 部件检测 ; 特征提取 ; 特征融合 ; 距离度量
地址

1. 中山大学智能工程学院, 广州, 510006  

2. 广东省智能交通系统重点实验室, 广东省智能交通系统重点实验室, 广州, 510006  

3. 视频图像智能分析与应用技术公安部重点实验室, 视频图像智能分析与应用技术公安部重点实验室, 广州, 510006  

4. 视频图像信息智能分析与共享应用技术国家工程实验室, 视频图像信息智能分析与共享应用技术国家工程实验室, 北京, 100048

语种 中文
文献类型 研究性论文
ISSN 1000-3428
学科 自动化技术、计算机技术
基金 国家自然科学基金
文献收藏号 CSCD:6513196

参考文献 共 15 共1页

1.  Mei L T. Application of automatic vehicle identification technology for real-time journey time estimation. Information Fusion,2011,12(1):11-19 被引 1    
2.  张耿宁. 基于特征融合的行人重识别方法. 计算机工程与应用,2017,53(12):185-189 被引 6    
3.  刘娜. 基于卷积神经网络的行人重识别算法,2017 被引 2    
4.  Cheng Deng. Person re-identification by multi-channel parts-based CNN with improved triplet loss function. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:1335-1344 被引 7    
5.  Tian Yin. A vehicle reidentification algorithm based on multi-sensor correlation. Journal of Zhejiang University-SCIENCE C (Computers and Electronics),2014,15(5):372-382 被引 1    
6.  Coifman B. Vehicle reidentification and travel time measurement,part II: uncongested freeways and the onset of congestion. Proceedings of 2001 IEEE Intelligent Transportation Systems,1999:899-917 被引 1    
7.  王盼盼. 基于特征融合和L-M算法的车辆重识别方法. 电子科技,2018,4(1):12-15 被引 1    
8.  Zhang Yiheng. Improving triplet-wise training of convolutional neural network for vehicle re-identification. Proceedings of IEEE International Conference on Multimedia and Expo,2017:1386-1391 被引 2    
9.  Xu Qingtong. Learning a repression network for precise vehicle search. Proceedings of IEEE CVPR'17,2017:125-136 被引 1    
10.  Zapletal D. Vehicle re-identification for automatic video traffic surveillance. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops,2016:1568-1574 被引 1    
11.  Zhou Yi. Vehicle re-identification by deep hidden multi-view inference. IEEE Transactions on Image Processing,2018,27(7):3275-3287 被引 8    
12.  Ren Shaoqing. Faster R-CNN: towards realtime object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149 被引 1823    
13.  Szegedy C. Going deeper with convolutions. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2015:1-9 被引 92    
14.  Macqueen J. Some methods for classification and analysis of multi-variate observations. Proceedings of Berkeley Symposium on Mathematical Statistics and Probability,1967:281-297 被引 8    
15.  Li Xiying. VRID-1: a basic vehicle re-identification dataset for similar vehicles. Proceedings of IEEE International Conference on Intelligent Transportation Systems,2017:1-8 被引 2    
引证文献 7

1 窦鑫泽 基于高置信局部特征的车辆重识别优化算法 北京航空航天大学学报,2020,46(9):1650-1659
被引 2

2 张小瑞 基于深度学习的车辆再识别研究进展 计算机工程,2020,46(11):1-11
被引 6

显示所有7篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号