Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor
https://doi.org/10.21122/2309-4923-2024-1-12-17
Abstract
For people re-identification in distributed video surveillance systems, it is important to have an algorithm that ensures efficiency when a person is blocked by other people or objects. Therefore, for this task, an algorithm has been developed that involves the compound descriptor formation, which includes a global features vector of a person’s image and three local ones for its upper, middle and down parts. The regions of interest selection is carried out based on the detecting key points results in the image of the human body. If a person's image part is occluded by other people or objects, then it is classified as invisible. The hidden part person image is not used in the formation of the local feature. To obtain it, the average value of the k-nearest neighbors such features of a person’s image is calculated. The experiments performed indicate an increase in re-identification accuracy for the Market-1501, DukeMTMC-ReID, MSMT17 and PolReID1077 datasets.
About the Authors
S. A. Ihnatsyeva
Euphrosyne Polotskaya State University of Polotsk
Belarus
Polotsk
Belarus
Polotsk
R. P. Bohush
Euphrosyne Polotskaya State University of Polotsk
Belarus
Polotsk
Belarus
Polotsk
References
1. Ihnatsyeva, S.A. Uvelichenie tochnosti reidentifikacii ljudej na osnove dvuhjetapnogo obuchenija svertochnyh nejronnyh setej i augmentacii / S.A. Ihnatsyeva, R.P. Bohush // Informatika. – 2023. – Vol. 20. – № 1. – Pр. 40-54.
2. Zhong, Z. Random Erasing Data Augmentation / Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang // AAAI Conference on Artificial Intelligence. – 2017.
3. Wang, G. High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification / G. Wang, S. Yang, H. Liu, Z. Wang, Y. Yang, S., Wang, G. Yu, E. Zhou, J. Sun // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). – 2020. – Pр. 6448-6457.
4. Yang, J. Learning to Know Where to See: A Visibility-Aware Approach for Occluded Person Re-identification / J. Yang, J. Zhang, F. Yu, X. Jiang, M. Zhang, X., Sun, Y. Chen, W. Zheng // 2021 IEEE/CVF International Conference on Computer Vision (ICCV). – 2021. – Pр. 11865-11874.
5. Yang, Q. Focus on the Visible Regions: Semantic-Guided Alignment Model for Occluded Person Re-Identification / Q. Yang, P. Wang, Z. Fang, Q. Lu. // Sensors (Basel, Switzerland), Vol. 20, 2020.
6. Sun, Y. Beyond Part Models: Person Retrieval with Refined Part Pooling / Y. Sun, L. Zheng, Y. Yang, Q. Tian, S. Wang // European Conference on Computer Vision, 2017.
7. Fang, H. RMPE: Regional Multi-person Pose Estimation / H. Fang, S. Xie, Y. Tai, C. Lu // Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. – Pр. 2353-2362.
8. Miao, J. Pose-Guided Feature Alignment for Occluded Person Re-Identification / J. Miao, Y. Wu, P. Liu, Y. Ding, Y. Yang // 2019 IEEE/CVF International Conference on Computer Vision (ICCV). – 2019. – Pр. 542-551.
9. Kalayeh, M.M. Human Semantic Parsing for Person Re-identification / M.M. Kalayeh, E. Basaran, M. Gokmen, M.E. Kamasak, M. Shah // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. – 2018. – Pр. 1062-1071.
10. GitHub [Электронный ресурс]. – Режим доступа: https://github.com/layumi/Person_reID_baseline_pytorch – Дата доступа 04.09.2023.
Review
For citations:
Ihnatsyeva S.A., Bohush R.P. Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor. «System analysis and applied information science». 2024;(1):12-17. (In Russ.) https://doi.org/10.21122/2309-4923-2024-1-12-17
Views:
234
Email this article 