Abstract
The task of person re-identification (re-ID) is to find the same pedestrian across non-overlapping camera views. Generally, the performance of person re-ID can be affected by background clutter. However, existing segmentation algorithms cannot obtain perfect foreground masks to cover the background information clearly. In addition, if the background is completely removed, some discriminative ID-related cues (i.e., backpack or companion) may be lost. In this article, we design a dual-stream network consisting of a Provider Stream (P-Stream) and a Receiver Stream (R-Stream). The R-Stream performs an a priori optimization operation on foreground information. The P-Stream acts as a pusher to guide the R-Stream to concentrate on foreground information and some useful ID-related cues in the background. The proposed dual-stream network can make full use of the a priori optimization and guided-learning strategy to learn encouraging foreground information and some useful ID-related information in the background. Our method achieves Rank-1 accuracy of 95.4% on Market-1501, 89.0% on DukeMTMC-reID, 78.9% on CUHK03 (labeled), and 75.4% on CUHK03 (detected), outperforming state-of-the-art methods.
- [1] . 2018. DensePose: Dense human pose estimation in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos, CA, 7297–7306.Google Scholar
Cross Ref
- [2] . 2014. 2D human pose estimation: New benchmark and state of the art analysis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14). 3686–3693. Google Scholar
Digital Library
- [3] . 2019. Mixed high-order attention network for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’19). 371–381.Google Scholar
Cross Ref
- [4] . 2019. ABD-Net: Attentive but diverse person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 8351–8361.Google Scholar
Cross Ref
- [5] . 2017. Person re-identification by deep learning multi-scale representations. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17). 2590–2600.Google Scholar
Cross Ref
- [6] . 2018. Batch DropBlock network for person re-identification and beyond. arXiv:1811.07130.Google Scholar
- [7] . 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09). IEEE, Los Alamitos, CA, 248–255.Google Scholar
Cross Ref
- [8] . 2010. Person re-identification by symmetry-driven accumulation of local features. In Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’10). IEEE, Los Alamitos, CA, 2360–2367.Google Scholar
Cross Ref
- [9] . 2009. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 9 (2009), 1627–1645. Google Scholar
Digital Library
- [10] . 2006. Person reidentification using spatiotemporal appearance. In Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2. IEEE, Los Alamitos, CA, 1528–1535. Google Scholar
Digital Library
- [11] . 2017. Accurate, large minibatch SGD: Training ImageNet in 1 hour. arXiv:1706.02677.Google Scholar
- [12] . 2019. Beyond human parts: Dual part-aligned representations for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’19). 3642–3651.Google Scholar
Cross Ref
- [13] . 2017. Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17). 2961–2969.Google Scholar
Cross Ref
- [14] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). 770–778.Google Scholar
Cross Ref
- [15] . 2017. In defense of the triplet loss for person re-identification. arXiv:1703.07737.Google Scholar
- [16] . 2015. Distilling the knowledge in a neural network. arXiv:1503.02531.Google Scholar
- [17] . 2017. DeepDiff: Learning deep difference features on human body parts for person re-identification. Neurocomputing 241 (2017), 191–203.Google Scholar
Cross Ref
- [18] . 2019. SBSGAN: Suppression of inter-domain background shift for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’19). 9527–9536.Google Scholar
Cross Ref
- [19] . 2019. Multi-pseudo regularized label for generated data in person re-identification. IEEE Transactions on Image Processing 28, 3 (2019), 1391–1403.Google Scholar
Digital Library
- [20] . 2020. Beyond scalar neuron: Adopting vector-neuron capsules for long-term person re-identification. IEEE Transactions on Circuits and Systems for Video Technology 30, 10 (2020), 3459–3471.Google Scholar
Cross Ref
- [21] . 2015. Spatial transformer networks. In Advances in Neural Information Processing Systems. 2017–2025. Google Scholar
Digital Library
- [22] . 2018. Human semantic parsing for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 1062–1071.Google Scholar
Cross Ref
- [23] . 2014. Adam: A method for stochastic optimization. arXiv:1412.6980.Google Scholar
- [24] . 2016. Superpixel-based background removal for accuracy salience person re-identification. In Proceedings of the 2016 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia’16). IEEE, Los Alamitos, CA, 1–4.Google Scholar
Cross Ref
- [25] . 2017. Learning deep context-aware features over body and latent parts for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 384–393.Google Scholar
Cross Ref
- [26] . 2014. DeepReid: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14). 152–159. Google Scholar
Digital Library
- [27] . 2017. Person re-identification by deep joint learning of multi-loss classification. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI’17). 2194–2200. Google Scholar
Digital Library
- [28] . 2018. Harmonious attention network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 2285–2294.Google Scholar
Cross Ref
- [29] . 2018. Look into person: Joint body parsing and pose estimation network and a new benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence 41, 4 (2018), 871–885. Google Scholar
Digital Library
- [30] . 2014. Microsoft COCO: Common objects in context. In Proceedings of the European Conference on Computer Vision (ECCV’14). 740–755.Google Scholar
Cross Ref
- [31] . 2017. End-to-end comparative attention networks for person re-identification. IEEE Transactions on Image Processing 26, 7 (2017), 3492–3506.Google Scholar
Digital Library
- [32] . 2019. An end-to-end foreground-aware network for person re-identification. arXiv:1910.11547.Google Scholar
- [33] . 2016. Background removal for improving saliency-based person re-identification. In Proceedings of the 2016 8th International Conference on Knowledge and Systems Engineering (KSE’16). IEEE, Los Alamitos, CA, 339–344.Google Scholar
Cross Ref
- [34] . 2017. Automatic differentiation in PyTorch. In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS’17). 1–4.Google Scholar
- [35] . 2018. MaskReid: A mask based deep ranking neural network for person re-identification. arXiv:1804.03864.Google Scholar
- [36] . 2018. Pose-normalized image generation for person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV’18). 650–667.Google Scholar
Digital Library
- [37] . 2018. Factorized distillation: Training holistic person re-identification model by distilling an ensemble of partial Reid models. arXiv:1811.08073.Google Scholar
- [38] . 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Proceedings of the European Conference on Computer Vision (ECCV’16). 17–35.Google Scholar
Cross Ref
- [39] . 2018. A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 420–429.Google Scholar
Cross Ref
- [40] . 2017. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17). 618–626.Google Scholar
Cross Ref
- [41] . 2018. Deep group-shuffling random walk for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 2265–2274.Google Scholar
Cross Ref
- [42] . 2018. Mask-guided contrastive attention model for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 1179–1188.Google Scholar
Cross Ref
- [43] . 2017. Pose-driven deep convolutional model for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17). 3960–3969.Google Scholar
Cross Ref
- [44] . 2018. Part-aligned bilinear representations for person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV’18). 402–419.Google Scholar
Digital Library
- [45] . 2017. SVDNet for pedestrian retrieval. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17). 3800–3808.Google Scholar
Cross Ref
- [46] . 2018. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European Conference on Computer Vision (ECCV’18). 480–496.Google Scholar
Digital Library
- [47] . 2016. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). 2818–2826.Google Scholar
Cross Ref
- [48] . 2018. Eliminating background-bias for robust person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 5794–5803.Google Scholar
Cross Ref
- [49] . 2018. Mancs: A multi-task attentional network with curriculum sampling for person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV’18). 365–381.Google Scholar
Digital Library
- [50] . 2018. Learning discriminative features with multiple granularities for person re-identification. In Proceedings of the 2018 ACM Multimedia Conference. ACM, New York, NY, 274–282. Google Scholar
Digital Library
- [51] . 2003. Silhouette analysis-based gait recognition for human identification. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 12 (2003), 1505–1518. Google Scholar
Digital Library
- [52] . 2017. Glad: Global-local-alignment descriptor for pedestrian retrieval. In Proceedings of the 25th ACM International Conference on Multimedia (MM’17). ACM, New York, NY, 420–428. Google Scholar
Digital Library
- [53] . 2019. Improving person re-identification performance using body mask via cross-learning strategy. In Proceedings of the 2019 IEEE Visual Communications and Image Processing (VCIP’19). IEEE, Los Alamitos, CA, 1–4.Google Scholar
Cross Ref
- [54] . 2018. Attention-aware compositional network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 2119–2128.Google Scholar
Cross Ref
- [55] . 2017. Divide and fuse: A re-ranking approach for person re-identification. arXiv:1708.04169.Google Scholar
- [56] . 2019. Densely semantically aligned person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 667–676.Google Scholar
Cross Ref
- [57] . 2017. Spindle Net: Person re-identification with human body region guided feature decomposition and fusion. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 1077–1085.Google Scholar
Cross Ref
- [58] . 2019. Pose invariant embedding for deep person re-identification. IEEE Transactions on Image Processing 28, 9 (2019), 4500–4509.Google Scholar
- [59] . 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’15). 1116–1124. Google Scholar
Digital Library
- [60] . 2016. Person re-identification: Past, present and future. arXiv:1610.02984.Google Scholar
- [61] . 2019. Re-identification with consistent attentive siamese networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19). 5735–5744.Google Scholar
Digital Library
- [62] . 2019. Joint discriminative and generative learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19).Google Scholar
Cross Ref
- [63] . 2018. A discriminatively learned CNN embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications 14, 1 (2018), 13. Google Scholar
Digital Library
- [64] . 2017. Re-ranking person re-identification with k-reciprocal encoding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 1318–1327.Google Scholar
Cross Ref
- [65] . 2019. Omni-scale feature learning for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’19).Google Scholar
Cross Ref
- [66] . 2019. Discriminative feature learning with foreground attention for person re-identification. arXiv:1807.01455.Google Scholar
- [67] . 2020. Identity-guided human semantic parsing for person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV’20).Google Scholar
Digital Library
Index Terms
Dual-Stream Guided-Learning via a Priori Optimization for Person Re-identification
Recommendations
Improving Person Re-identification by Background Subtraction Using Two-Stream Convolutional Networks
Image Analysis and RecognitionAbstractThe field of person re-identification is facing problems related to the variation of illumination and background scenes. In order to reduce the impact of those variations, we propose in this work a two-stream re-identification system based on a ...
Foreground-guided textural-focused person re-identification
AbstractPerson re-identification (Re-ID) is challenging in computer vision. It is crucial to strengthen discriminative features and suppress irrelevant ones for high-performance. Existing Re-ID approaches have won significant progress by ...
Person re-identification: A taxonomic survey and the path ahead
AbstractPerson re-identification (PRId) is one of the most challenging tasks in automated video surveillance and has been an area of intense research spanning the past decade. PRId aims at finding a person who has previously been identified ...
Graphical abstractDisplay Omitted
Highlights- Presents a methodology based taxonomy for the state-of-the-art strategies in PRId.






Comments