Abstract
The person re-identification (re-ID) problem refers to identifying people with the same identity in the context of a multi-camera system, which is a computer vision task with great development potential. However, this is still a difficult task due to blurred images and different shooting environments. Thus, we proposed a self-guided network (SGN) for person re-identification. Firstly, based on ResNet50, a four-branch network with non-shared weights is designed to effectively extract both local and global features. To enhance the diversity of different local branches, a mutex activation penalty mechanism is added. Finally, SGN is jointly trained with the overlap activation penalty loss and the identity classification loss. The performance of the proposed method is tested with three public datasets. Our method has reached Rank-1/mAP of 93.65%/81.91% on Market-1501, 86.27%/71.70% on Duke-MTMC-reID, and 74.62%/46.18% on MSMT17.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sumari, F.O., Machaca, L., Huaman, J., Clua, E.W.G., Guérin, J.: Towards practical implementations of person re-identification from full video frames. J. Pattern Recogn. Lett. 138, 513–519 (2020)
Huang, Y., Zha, Z., Fu, X., Hong, R., Li, L.: Real-world person re-identification via degradation invariance learning In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14084–14094. IEEE (2020)
Guo, L., Wang, R., Zhang, M., Jin, L.: Pedestrian detection method based on Adaboost algorithm. J. Comput. Eng. 34, 202–204 (2008)
Guo, L., Zhang, M., Li, L., Zhao, Y.: Research on pedestrian recognition method based on support vector machine. J. Dalian Univ. Technol. 4, 604–610 (2011)
Liu, Q., Hou, L., Peng, Z.: Pedestrian re-identification based on ininvariant feature and kernel distance metric learning. J. Image Sig. Process. 7, 9 (2018)
Li, Y., Zhuo, L., Zhang, J., Li, J., Zhang, H.: Review of pedestrian re-identification technology. J. Acta Automatica Sinica. 44, 1554–1568 (2018)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of ECCV (2018)
Yao, H., Zhang, S., Zhang, Y., et al.: Deep representation learning with part loss for person re-identification. IEEE Trans. Image Process. 28(6), 2860–2871 (2019)
Zhao, L., Xi, L., Zhuang, Y., Wang, J.: Deeply-learned part-aligned representations for person re-identification. In: 2017 IEEE International Conference on Computer Vision (ICCV), IEEE (2017)
Ding, G., Khan, S., Tang, Z., Porikli, F.: Feature mask network for person re-identification. J. Pattern Recognit. Lett. 137, 91–98 (2020)
Li, W., Zhu, X., Gong, S.: Harmonious attention network for person re-identification. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE (2018)
Bai, X., Yang, M., Huang, T., Dou, Z., Yu, R., Xu, Y.: Deep-person: learning discriminative deep features for person re-identification. J. Pattern Recognit. 98, 107036 (2020)
Yang, W., Huang, H., Zhang, Z., Chen, X., Zhang, S.: Towards rich feature discovery with class activation maps augmentation for person re-identification, In: IEEE Conference on Computer Vision and Pattern Recognition 2019, IEEE (2019)
Sun, Y., Zheng, L., Deng, W., Wang, S.: SVDNet for pedestrian retrieval. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE Computer Society (2017)
Shen, Y., Li, H., Yi, S., Chen, D., Wang, X.: Person reidentification with deep similarity-guided graph neural network. In: Proceedings of ECCV (2018)
Zheng, L., Huang, Y., Lu, H., Yang, Y.: Pose-invariant embedding for deep person re-identification. IEEE Trans. Image Process. 28(9), 4500–4509 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016).
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of ICCV (2015)
Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multicamera tracking. In: Proceedings of ECCV (2016)
Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridgedomain gap for person reidentification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Acknowledgments
This research is supported by the National Training Program of Innovation and Entrepreneurship for Undergraduates of Beijing Jiaotong University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, Z., Zhang, Z., Chen, Z., Li, Y. (2022). Improving Person Re-identification by Rich Feature Discovery with Self-guided Network. In: Li, X. (eds) Advances in Intelligent Automation and Soft Computing. IASC 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 80. Springer, Cham. https://doi.org/10.1007/978-3-030-81007-8_88
Download citation
DOI: https://doi.org/10.1007/978-3-030-81007-8_88
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-81006-1
Online ISBN: 978-3-030-81007-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)