Abstract
The vehicle re-identification task aims to retrieve the same vehicle from multiple cameras. One of the challenges of this task is that images of different vehicles may look very similar under the same perspective, which affects the performance of vehicle re-identification tasks. Recent studies have shown that the attention mechanism is effective for vehicle re-identification, because it encourages models to focus on information related to the identity of the target rather than interference information such as background. In this paper, we first propose a dual-relational attention module (DRAM), which simultaneously constructs the importance of a feature point in the spatial and channel dimensions, and further models the attention of the feature point in the three-dimensional space. Then, we integrate the dual-relational attention module into a three-branch network, called dual-relational attention network (DRA-Net). In addition, to ensure that the network can extract a large number of diverse information, we add a non-similarity constraint in dual-relational attention network (DRA-Net) to make different branches focus on different locations in an image. In the experiments, our method is verified on two datasets (VeRi-776 and VehicleID), and the experimental results indicate that the proposed method is superior to several advanced methods.
Similar content being viewed by others
Data Availability
All data included in this study are available upon request by contact with the corresponding author.
References
Chen T, Ding S, Xie J, et al. (2019) ABD-Net: Attentive but Diverse Person Re-Identification. In: IEEE international conference on computer vision (ICCV), pp 8350–8360
Woo S, Park J, Lee J, et al. (2018) CBAM: Convolutional Block Attention Module. In: European conference on computer vision (ECCV), pp 3–19
Liu K, Xu Z, Hou Z, et al. (2020) Further Non-local and Channel Attention Networks for Vehicle Re-identification. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 2494–2500
Bryan X, Gong Y et al (2019) Second-order Non-local Attention Networks for Person Re-identification. In: IEEE international conference on computer vision (ICCV), pp 3759–3768
Wang X, Girshick R, Gupta A et al (2018) Non-local Neural Networks. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 7794–7803
Zhang Z, Lan C, Zeng W et al (2020) Relation-Aware Global Attention for Person Re-Identification. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 3183–3192
Liu H, Tian Y, Wang Y et al (2016) Deep Relative Distance Learning: Tell the Difference between Similar Vehicles. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 2167–2175
Ke Y, Tian Y, Wang Y et al (2017) Exploiting Multi-grain Ranking Constraints for Precisely Searching Visually-similar Vehicles. In: IEEE international conference on computer vision (ICCV), pp 562–570
Wang Z, Tang L, Liu X et al (2017) Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification. In: IEEE international conference on computer vision (ICCV), pp 379–387
Shen Y, Tong X, Li H et al (2017) Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals. In: IEEE international conference on computer vision (ICCV), pp 1918–1927
Liu X, Wu L, Tao M et al (2016) A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance. In: European conference on computer vision (ECCV), pp 869–884
Zapletal D, Herout A (2016) Vehicle Re-identification for Automatic Video Traffic Surveillance. In: IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp 1568–1574
Liu W, Wen Y, Yu Z et al (2016) Large-Margin Softmax Loss for Convolutional Neural Networks. In: Thirty-Eighth International Conference on Machine Learning(ICML), pp 507–516
Hermans A, Beyer L, Leibe B (2017) In Defense of the Triplet Loss for Person Re-Identification. arXiv:1703.07737
Zheng Z, Zheng L, Garrett M et al (2020) Dual-Path Convolutional Image-Text Embedding. In: ACM Transactions on Multimedia Computing, Communications, and Applications, pp 51:1– 51:23
Zhang Y, Dong L, Zha Z (2017) Improving triplet-wise training of convolutional neural network for vehicle re-identification. In: IEEE international conference on multimedia and expo(ICME), pp 1386–1391
Yuan Y, Yang K, Zhang C (2017) Hard-Aware Deeply Cascaded Embedding. In: IEEE international conference on computer vision (ICCV), pp 814–823
Xu Q, Yan K, Tian Y (2017) Learning a Repression Network for Precise Vehicle Search. arXiv:1708.02386
Zhou Y, Shao L (2017) Cross-View GAN Based Vehicle Generation for Re-identification. In: British Machine Vision Conference(BMVC)
Yi Z, Ling S (2018) Viewpoint-Aware Attentive Multi-view Inference for Vehicle Re-identification. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 6489–6498
Fei W, Jiang M, Chen Q et al (2017) Residual Attention Network for Image Classification. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 6450–6458
Lin C, Lu J, Wang G et al (2018) Graininess-Aware Deep Feature Learning for Pedestrian Detection. In: European conference on computer vision (ECCV), pp 745–761
Jie H, Li S, Gang S et al (2018) Squeeze-and-Excitation Networks. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 7132–7141
Zhang Y, Li K, Li K et al (2018) Image Super-Resolution Using Very Deep Residual Channel Attention Networks. In: European conference on computer vision (ECCV), pp 294–310
Liu H, Feng J, Qi M et al (2017) End-to-End Comparative Attention Networks for Person Re-Identification. In: IEEE transactions on image processing, pp 3492–3506
Cheng W, Qian Z, Chang H et al (2018) Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification. In: European conference on computer vision (ECCV), pp 384–400
Gao S, Wang J, Lu, H et al (2020) Pose-guided Visible Part Matching for Occluded Person ReID. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 11741–11749
Zhang X, Luo H, Fan X et al (2017) AlignedReID: Surpassing Human-Level Performance in Person Re-Identification. arXiv:1711.08184
Sun Y, Zheng L, Yang Y et al (2018) Beyond Part Models: Person Retrieval with Refined Part Pooling. In: European conference on computer vision (ECCV), pp 501–518
Bai X, Yang M, Huang T et al (2017) Deep-Person: Learning Discriminative Deep Features for Person Re-Identification. In: Pattern Recognition
Kingma D, Ba J (2015) Adam: A Method for Stochastic Optimization. In: Tenth international conference on learning representations(ICLR)
Lou Y, Bai Y, Liu J et al (2019) Embedding Adversarial Learning for Vehicle Re-Identification. In: IEEE Transactions on Image Processing, pp 1–1
Liu X, Zhang S, Huang Q et al (2018) RAM: A Region-Aware Deep Model for Vehicle Re-Identification. In: IEEE international conference on multimedia and expo(ICME), pp 1–6
Khorramshahi P, Kumar A, Peri N et al (2019) A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification. In: IEEE international conference on computer vision (ICCV), pp 6131–6140
Kanaci A, Li M, Gong S et al (2019) Multi-Task Mutual Learning for Vehicle Re-Identification. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 62–70
Zhu J, Zeng H, Huang J et al (2019) Vehicle Re-Identification Using Quadruple Directional Deep Learning Features. In: IEEE Transactions on Intelligent Transportation Systems, pp 1–11
Chen T, Lee M, Liu C et al (2020) Viewpoint-Aware Channel-Wise Attentive Network for Vehicle Re-Identification. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 2448–2455
He B, Li J, Zhao Y et al (2019) Part-Regularized Near-Duplicate Vehicle Re-Identification. In: IEEE conference on computer vision and pattern recognition(CVPR), pp 3997–4005
Wang H, Peng J, Jiang G et al (2021) Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification. Neurocomputing 438(12)
Peng J, Jiang G, Wang H (2021) Generalized multiple sparse information fusion for vehicle re-identification. J Vis Commun Image Represent 79:103207
Teng S, Zhang S, Huang Q et al (2021) Viewpoint and Scale Consistency Reinforcement for UAV Vehicle Re-Identification. Int J Comput Vis 129(3):719–735
Fu X, Peng J, Jiang G et al (2022) Learning latent features with local channel drop network for vehicle re-identification. Eng Appl Artif Intell 107:104540
Du L, Yu C, Shuai C et al (2021) A Multiscale Attention Mechanism Based Vehicle Re-Identification. ICSAI:1–6
Qian J, Jiang W, Luo H et al (2019) Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification. arXiv:1910.05549
Khorramshahi P, Peri N, Chen J et al (2020) The Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification. In: European conference on computer vision (ECCV), pp 369– 386
Li K, Ding Z, Li K, et al. (2022) Vehicle and Person Re-Identification With Support Neighbor Loss. IEEE Trans Neural Netw Learn Syst 33(2):826–838
Acknowledgements
This work is supported by the Focus on Research and Development Plan in Shandong Province NO.2019GGX101055, and the Shandong Education Science “13th five year plan” special project “Research on examinee online identity verification system based on multimodal biometrics” NO. BYZK201904.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zheng, Y., Pang, X., Jiang, G. et al. Dual-relational attention network for vehicle re-identification. Appl Intell 53, 7776–7787 (2023). https://doi.org/10.1007/s10489-022-03801-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03801-z