Abstract
The paper is aimed to improve person re-identification accuracy in distributed video surveillance systems based on constructing a large joint image dataset of people for training convolutional neural networks (CNN). For this aim, an analysis of existing datasets is provided. Then, a new large joint dataset for person re-identification task is constructed that includes the existing public datasets CUHK02, CUHK03, Market, Duke, MSMT17 and PolReID. Testing for re-identification is performed for such frequently cited CNNs as ResNet-50, DenseNet121 and PCB. Re-identification accuracy is evaluated by using the main metrics Rank, mAP and mINP. The use of the new large joint dataset makes it possible to improve Rank1 mAP, mINP on all test sets. Re-ranking is used to further increase the re-identification accuracy. Presented results confirm the effectiveness of the proposed approach.
Publisher
Warsaw University of Life Sciences - SGGW Press
Subject
Computer Graphics and Computer-Aided Design,Computer Vision and Pattern Recognition,Software
Reference45 articles.
1. A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao. YOLOv4: Optimal speed and accuracy of object detection. arXiv, 2020. arXiv:2004.10934. https://doi.org/10.48550/arXiv.2004.10934.
2. S. Bąk and P. Carr. One-shot metric learning for person re-identification. In Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2017), pages 1571-1580, Honolulu, HI, USA, 21-26 Jul 2017. https://doi.org/10.1109/CVPR.2017.171.
3. Y. Dai, J. Liu, Y. Sun, et al. IDM: An intermediate domain module for domain adaptive person re-ID. In Proc. 2021 IEEE/CVF Conf. Computer Vision (ICCV 2021), pages 11844-11854, Montreal, QC, Canada, 10-17 Oct. https://doi.org/10.1109/ICCV48922.2021.01165.
4. Y. Dai, Y. Sun, J. Liu, et al. Bridging the source-to-target gap for cross-domain person re-identification with intermediate domains. ArXiv, 2022. arXiv:2203.01682v1. https://doi.org/10.48550/arXiv.2203.01682.
5. Z. Ding, C. Ding, Z. Shao, and D. Tao. Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv, 2021. arXiv:2107.12666v2. https://doi.org/10.48550/arXiv.2107.12666.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献