[1]曹仰杰,蔡吉灏,王沛祺,等.一种抗行人干扰的车辆重识别算法[J].郑州大学学报(工学版),2026,47(XX):1-7.[doi:10.13705/j.issn.1671-6833.2025.05.012]
　CAO Yangjie,CAI Jihao,WANG Peiqi,et al.A Vehicle Re-identification Post-processing Algorithm Against Pedestrian Interference[J].Journal of Zhengzhou University (Engineering Science),2026,47(XX):1-7.[doi:10.13705/j.issn.1671-6833.2025.05.012]
点击复制

一种抗行人干扰的车辆重识别算法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
47
期数:
2026年XX
页码:
1-7
栏目:
出版日期:
2026-09-10

文章信息/Info

Title:
A Vehicle Re-identification Post-processing Algorithm Against Pedestrian Interference
作者:
曹仰杰1; 2; 蔡吉灏1; 2; 王沛祺1; 2; 杨聪1; 2
1.郑州大学 网络空间安全 学院,河南 郑州 450002;2.河南省智能感知与处理工程研究中心,河南 郑州 450002
Author(s):
CAO Yangjie1; 2;  CAI Jihao1; 2;  WANG Peiqi1; 2;  Yang Cong1; 2
1.School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China;2.Henan Province Engineering Research Center of Intelligent Sensing and Processing, Zhengzhou 450002
关键词:
车辆重识别; 行人干扰; 轨迹优化; 背景抑制; 特征提取
Keywords:
vehicle re-identification;  pedestrian interference;  track refinement;  background suppression;  feature extraction
分类号:
TP391
DOI:
10.13705/j.issn.1671-6833.2025.05.012
文献标志码:
A
摘要:
车辆重识别是实现车辆跟踪的基础，然而，行人干扰会显著影响车辆特征的提取，进而降低车辆重识别的准确性和精度。针对这一问题，提出一种名为轨迹优化与背景抑制的车辆重识别算法TRaBS。首先，使用ResNeXt101-IBN-a网络对车辆图像进行特征提取，得到初始车辆特征，同时应用背景抑制算法对摄像头画面进行特征计算，生成经过背景抑制处理的车辆特征；其次，为了降低行人对特征提取的干扰，采用欧几里得距离和高斯核函数，将车辆图像特征替换为更加稳定的轨迹特征。通过这些技术，TRaBS算法有效解决了车辆重识别中的行人干扰问题；最后，为全面验证TRaBS算法在应对行人干扰方面的有效性以及在无干扰环境下的通用性，设计并进行了大量对比实验与消融实验。实验结果表明：融合轨迹优化与背景抑制算法的车辆重识别模型在基准数据集以及引入行人干扰的衍生数据集上均取得了显著的性能提升。在VeRi-776数据集上，平均精确度mAP达到83.6%，Rank-1准确率达到了97.6%，显著优于现有主流方法。
Abstract:
Vehicle re-identification serves as the foundation for vehicle tracking. However, pedestrian interference was found to significantly degrade the quality of feature extraction, thereby reducing the accuracy and precision of vehicle re-identification. To address this issue, a vehicle re-identification algorithm named TRaBS was proposed, which incorporates trajectory optimization and background suppression techniques. First, ResNeXt101-IBN-a was employed to extract initial features from vehicle images, while a background suppression algorithm was applied to the camera frames to generate background-suppressed vehicle features. Second, to mitigate the impact of pedestrian interference on feature extraction, Euclidean distance and Gaussian kernel functions were utilized to replace image-level features with more stable trajectory-level representations. Through these techniques, the problem of pedestrian-induced interference in vehicle re-identification was effectively alleviated. To comprehensively evaluate the effectiveness of TRaBS in handling pedestrian interference and its generalization ability in interference-free scenarios, extensive comparative and ablation experiments were conducted. Experimental results demonstrated that the vehicle re-identification model integrated with trajectory optimization and background suppression achieved significant performance improvements on both benchmark datasets and derivative datasets with pedestrian interference. Specifically, on the VeRi-776 dataset, the model achieved a mean Average Precision (mAP) of 83.6% and a Rank-1 accuracy of 97.6%, outperforming existing state-of-the-art methods.

参考文献/References:

[1] HAN K, GONG S G, HUANG Y, et al. Clothing-change feature augmentation for person re-identification[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Piscataway: IEEE, 2023: 22066-22075.
[2] GAO Y L, LU L P, XU B R, et al. Multi-dimensional attention network for vehicle re-identification[C]//2022 6th CAA International Conference on Vehicular Control and Intelligence (CVCI). Piscataway: IEEE, 2022: 1-5.
[3] KHORRAMSHAHI P, SHENOY V, CHELLAPPA R. Robust and scalable vehicle re-identification via self-supervision[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE, 2023: 5295-5304.
[4] WANG Y, PENG J J, WANG H B, et al. Progressive learning with multi-scale attention network for cross-domain vehicle re-identification[J]. Science China Information Sciences, 2022, 65(6): 160103.
[5] LUO H, JIANG W, GU Y Z, et al. A strong baseline and batch normalization neck for deep person re-identification[J]. IEEE Transactions on Multimedia, 2020, 22(10): 2597-2609.
[6] YE M, SHEN J B, LIN G J, et al. Deep learning for person re-identification: a survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(6): 2872-2893.
[7] NABILA E S, Wahyono. Person re-identification using background subtraction and Siamese network for pose variants[C]//2022 8th International Conference on Science and Technology (ICST). Piscataway: IEEE, 2022: 1-6.
[8] ZHOU Z L, LI Y J, LI J, et al. GAN-Siamese network for cross-domain vehicle re-identification in intelligent transport systems[J]. IEEE Transactions on Network Science and Engineering, 2023, 10(5): 2779-2790.
[9] LEE S, WOO T, LEE S H. Multi-attention-based soft partition network for vehicle re-identification[J]. Journal of Computational Design and Engineering, 2023, 10(2): 488-502.
[10] NGUYEN N B, NGUYEN V H, NGO T D, et al. Person re-identification with mutual re-ranking[J]. Vietnam Journal of Computer Science, 2017, 4(4): 233-244.
[11] MANSOURIAN A M, SOMERS V, DE VLEESCHOUWER C, et al. Multi-task learning for joint re-identification, team affiliation, and role classification for sports visual tracking[C]//Proceedings of the 6th International Workshop on Multimedia Content Analysis in Sports. New York: ACM, 2023: 103-112.
[12] CHEN Y H, WANG C Y, YANG C Y, et al. NeighborTrack: improving single object tracking by bipartite matching with neighbor tracklets[EB/OL]. (2022-11-12)[2025-02-18]. https://doi.org/10.48550/arXiv.2211.06663.
[13] LIU X C, LIU W, MA H D, et al. Large-scale vehicle re-identification in urban surveillance videos[C]//2016 IEEE International Conference on Multimedia and Expo (ICME). Piscataway: IEEE, 2016: 1-6.
[14] LIU H Y, TIAN Y H, WANG Y W, et al. Deep relative distance learning: tell the difference between similar vehicles[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2016: 2167-2175.
[15] HE Z Q, LEI Y, BAI S, et al. Multi-Camera Vehicle Tracking with Powerful Visual Features and Spatial-Temporal Cue[C]//CVPR Workshops. Piscataway: IEEE, 2019: 203-212.
[16] BOSER B E, GUYON I M, VAPNIK V N. A training algorithm for optimal margin classifiers[C]//Proceedings of the Fifth Annual Workshop on Computational Learning Theory. Pittsburgh Pennsylvania USA. New York: ACM, 1992: 144-152.
[17] XIE S N, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017: 5987-5995.
[18] ZHONG Z, ZHENG L, CAO D L, et al. Re-ranking person re-identification with k-reciprocal encoding[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017: 3652-3661.
[19] LIN W P, LI Y D, YANG X L, et al. Multi-view learning for vehicle re-identification[C]//2019 IEEE International Conference on Multimedia and Expo (ICME). Piscataway: IEEE, 2019: 832-837.
[20] JIN Y, LI C N, LI Y D, et al. Model latent views with multi-center metric learning for vehicle re-identification[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1919-1931.
[21] QIAN J C, PAN M T, TONG W, et al. URRNet: a unified relational reasoning network for vehicle re-identification[J]. IEEE Transactions on Vehicular Technology, 2023, 72(9): 11156-11168.
[22] XU Z M, WEI L L, LANG C Y, et al. SSR-net: a structural translation network for vehicle re-identification[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2023, 19(6): 1-22.
[23] PANG X Y, TIAN X, NIE X S, et al. Vehicle re-identification based on grouping aggregation attention and cross-part interaction[J]. Journal of Visual Communication and Image Representation, 2023, 97: 103937.

备注/Memo

备注/Memo:
收稿日期:2025-04-23;修订日期:2025-06-02
基金项目:国家自然科学基金资助项目(62302458) ;河南省青年科学基金资助项目( 242300421474) ;河南省科技攻关资助项目(222102310547)
作者简介:曹仰杰(1976— ) ,男,河南濮阳人,郑州大学教授,博士,博士生导师,主要从事智能系统与安全研究,E-mail:caoyj@ zzu. edu. cn。
通信作者:杨聪(1987— ) ,男,四川达州人,郑州大学副教授,主要从事深度学习,计算机视觉等方向的研究,E-mail：wangyuanyc@zzu.edu.cn。
更新日期/Last Update: 2026-01-14