Smart City Gnosys
Smart city article details
| Title | Paii: A Pose Alignment Network With Information Interaction For Person Re-Identification |
|---|---|
| ID_Doc | 41192 |
| Authors | Lyu C.; Xu T.; Ning W.; Cheng Q.; Wang K.; Wang C. |
| Year | 2023 |
| Published | Neural Processing Letters, 55, 2 |
| DOI | http://dx.doi.org/10.1007/s11063-022-10947-x |
| Abstract | As an important part of intelligent surveillance systems, person re-identification (re-ID) has a wide range of application prospects in smart cities. However, due to occlusion, viewpoint variation, and background shift, the misalignment problem always decreases the re-ID systems’ effects. To solve this problem, a pose alignment network with information interaction (PAII) is proposed. This approach consists of three cascaded modules. First, guided by a pretrained pose estimator, the backbone with a dual attention block is used to obtain local features corresponding to different pose keypoints along with the global feature. Then, a pose alignment module is constructed to group these local features into different parts and fuse them with a hyperparameter λ, which provides the possibility to achieve semantic alignment. Finally, since different semantic features are extracted, an information interaction module consisting of graph attention layers is made to conduct message passing between different semantic features. All semantic features and the global feature are used to calculate the loss functions. Our approach considers multi-scale representations and information interaction of semantic features, which makes it more robust to misalignment problems. Thus, the proposed PAII method achieves better performance than most existing methods on multiple popular re-ID datasets. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. |
| Author Keywords | Information interaction; Person re-identification; Pose estimation; Semantic alignment |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
42375  | 0.878 | HE Z.; ZHAO H.; WANG J.; FENG W. | Pose Matters: Pose Guided Graph Attention Network For Person Re-Identification | Chinese Journal of Aeronautics, 36, 5 (2023) |
| 51477 | 0.865 | Perwaiz N.; Fraz M.M.; Shahzad M. | Smart Surveillance With Simultaneous Person Detection And Re-Identification | Multimedia Tools and Applications, 83, 5 (2024) |
| 28943 | 0.864 | Li Y.; Lian G.; Zhang W.; Ma G.; Ren J.; Yang J. | Heterogeneous Feature-Aware Transformer-Cnn Coupling Network For Person Re-Identification | PeerJ Computer Science, 8 (2022) |
| 7827 | 0.857 | Maqsood M.; Yasmin S.; Gillani S.; Bukhari M.; Rho S.; Yeo S.-S. | An Efficient Deep Learning-Assisted Person Re-Identification Solution For Intelligent Video Surveillance In Smart Cities | Frontiers of Computer Science, 17, 4 (2023) |
| 5185 | 0.857 | Li Q.; Hu W.-Y.; Li J.-Y.; Liu Y.; Li M.-X. | A Survey Of Person Re-Identification Based On Deep Learning; [基于深度学习的行人重识别方法综述] | Gongcheng Kexue Xuebao/Chinese Journal of Engineering, 44, 5 (2022) |
| 4278 | 0.853 | Selvan C.; Anwar Basha H.; Meenakshi K.; Naveen S. | A Review On Person Re-Identification Techniques And Its Analysis | IEEE Access, 13 (2025) |
| 46058 | 0.851 | Qammar J.; Ahmad W. | Resolution Representation Based Person Re-Identification For Smart Cities Using Deep Neural Networks (Dnns) | 2021 International Conference on Information Technology, ICIT 2021 - Proceedings (2021) |