Robust Person Identification with Channel Attention and Multi-Scale Feature Extraction
Bilah Samping Artikel
Diterbitkan:
Mar 31, 2026
Isi Artikel Utama
Abstrak
Person recognition under varied conditions is a critical task that aims to accurately identify individuals captured from different angles or at different times. One of the primary challenges in this field is occlusion, which significantly degrades recognition performance. To address this issue, we propose an advanced attention-based network designed to mitigate the effects of occlusion and enhance recognition accuracy. Our approach leverages channel attention to dynamically recalibrate the importance of each channel, utilizing both width and depth attention mechanisms to emphasize discriminative and informative features. The network employs a multi-scale feature extraction strategy, partitioning feature maps to capture multi-level representations of the human body. The concatenation of results from these attention stages facilitates the integration of local and global features, effectively reducing the impact of occlusion. We evaluate the proposed model on multiple benchmark datasets, including PRID 2011, iLIDS-VID, and Market-1501. The experimental results demonstrate that our model achieves superior performance, attaining a top accuracy of 99.79% on the PRID 2011 dataset, 98.55% on the iLIDS-VID dataset, and 88.24% on the Market-1501 dataset.
Rincian Artikel
##submission.howToCite##
R, N. S., S, A., J, K., & S, S. G. (2026). Robust Person Identification with Channel Attention and Multi-Scale Feature Extraction . JITSI : Jurnal Ilmiah Teknologi Sistem Informasi, 7(1), 27 - 35. https://doi.org/10.62527/jitsi.7.1.543
Terbitan
Bagian
Articles
##submission.license.cc.by-sa4.footer##
Referensi
[1] M. Cokbas, J. Bolognino, J. Konrad, and P. Ishwar, “FRIDA: Fisheye re-identification dataset with annotations,” in Proc. 18th IEEE Int. Conf. Adv. Video Signal Based Surveillance (AVSS), Nov. 2022, pp. 1–8.
[2] N. V. Mahendran, “Variations of squeeze and excitation networks,” arXiv e-prints, arXiv:2304.06502v2 [cs.CV], Jul. 3, 2023.
[3] Q. Xie, Z. Lu, W. Zhou, and H. Li, “Improving person re-identification with multi-cue similarity embedding and propagation,” IEEE Trans. Multimedia, 2022.
[4] C. Gong, J. Hu, L. Zhang, W. Liu, and X. Wang, “Spatio-temporal multi-graph convolutional network for video person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023.
[5] W. Hu, L. Wang, and C. Peng, “A method for detecting anomalies in an electromagnetic environment situation using a dual-branch prediction network,” Electronics, vol. 11, no. 16, p. 2555, 2022.
[6] Z. Jiang, Y. Wang, W. Liu, L. Zhang, and J. Chen, “GLAF: Group-based local affinity feature for cross-domain person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023.
[7] X. Wang, Y. Zhang, J. Li, W. Liu, and J. Chen, “Deep multi-resolution network for person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023.
[8] X. Zhang, X. Zhang, L. Wu, C. Li, X. Chen, and X. Chen, “Domain adaptation with self-guided adaptive sampling strategy: Feature alignment for crossuser myoelectric pattern recognition,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 1374–1383, 2022.
[9] Y. Lu, M. Jiang, Z. Liu, and X. Mu, “Dual-branch adaptive attention transformer for occluded person re-identification,” Image Vis. Comput., vol. 131, p. 104633, 2023.
[10] Wencheng Qin, Baojin Huang, Pinzhong Qin, Zhiyong Huang, Daidi Zhong, Learning diverse and deep clues for person reidentification, Image and Vision Computing, Volume 126, 2022, 104551, ISSN 0262-8856, https://doi.org/10.1016/j.imavis.2022.104551.
[11] Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2021). Attention Mechanisms in Computer Vision: A Survey. arXiv. https://doi.org/10.48550/ARXIV.2111.07624
[12] L. Li, B. Chen, K. Huang, et al., “Multiscale attention graph neural networks for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023.
[13] J. Si, H. Zhang, C. G. Li, J. Kuen, X. Kong, A. C. Kot, and G. Wang, “Dual attention matching network for context-aware feature sequencebased person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 5363–5372.
[14] Z. Zhang, C. Lan, W. Zeng, X. Jin, and Z. Chen, “Relation-aware global attention for person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 3186–3195.
[15] H. Zhan, L. Zheng, Y. Wang, et al., “Pose-guided attention network for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021.
[16] A. Mohanty, B. Banerjee, and R. Velmurugan, “SSMTReID-Net: Multi-target unsupervised domain adaptation for person re-identification,” Pattern Recognit. Lett., vol. 163, pp. 40–46, 2022.
[17] Z. Pang, L. Zhao, Q. Liu, and C. Wang, “Camera invariant feature learning for unsupervised person re-identification,” IEEE Trans. Multimedia, 2022.
[18] R. Zhang, Y. Fan, H. Song, F. Wan, Y. Fu, H. Kato, and Y. Wu, “A novel retrieval-verification framework for cloth changing person re-identification,” Pattern Recognit., vol. 134, 2023.
[19] X. Wei, K. Song, W. Yang, Y. Yan, and Q. Meng, “A visible infrared clothes-changing dataset for person re-identification in natural scene,” Neurocomputing, vol. 569, p. 127110, 2024.
[20] M. Shao and H. Ling, “Dynamic curriculum learning for weakly supervised person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023.
[21] X. Yu, J. Song, Y.-Z. Song, et al., “Weakly supervised person re-identification with multi-level self-paced learning,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023.
[22] C. Shi, D. Niu, H. Gong, M. Zhang, Z. Cao, and Y. Jin, “Person reidentification lightweight network based on progressive attention mechanism,” in Proc. Int. Symp. Autonomous Syst. (ISAS), Jun. 2023, pp. 1– 6.
[23] Y. Ge, F. Zhu, X. Liu, et al., “Triplet probability learning for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020.
[24] S. Xu, Y. Hou, Z. Li, and D. Cao, “Joint face and person re-identification with bilinear transformation networks,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 9, pp. 3347–3360, Sep. 2021.
[25] Z. Zheng, X. Zhu, S. Gong, et al., “Learning to fuse local and global representations for person re-identification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 7, pp. 2429–2442, Jul. 2023.
[26] Q. Leng, M. Ye, and Q. Tian, “A survey of open-world person reidentification,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 4, pp. 1092–1108, Apr. 2019.
[27] X. Zhu, J. Zhang, J. Shi, et al., “Deep fusion of global and local representations for person re-identification,” IEEE Trans. Image Process., vol. 32, pp. 1576–1589, 2023.
[28] J. Liu, Y. Chen, X. Nie, et al., “Adaptive feature fusion network for occlusionaware person re-identification,” Pattern Recognit., 2023.
[29] X. Zhang, Z. Zhang, H. Chen, et al., “Learning to adapt template for person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021.
[30] X. Xu, S. Liu, N. Zhang, G. Xiao, and S. Wu, “Channel exchange and adversarial learning guided cross-modal person re-identification,” Knowl.-Based Syst., vol. 257, p. 109883, 2022.
[31] L. Machaca, J. Huaman, E. Clua, and J. Guerin, “TrADe Re-ID–Live person re-identification using tracking and anomaly detection,” in Proc. IEEE Int. Conf. Mach. Learn. Appl. (ICMLA), Dec. 2022, pp. 449–454.
[32] X. Zang, G. Li, W. Gao, and X. Shu, “Learning to disentangle scenes for person re-identification,” Image Vis. Comput., vol. 116, p. 104237, Dec. 2021.
[33] S. Chen, S. Chen, and Z. Lei, “FAS-ReID: Fair architecture search for person re-identification,” in Proc. IEEE Int. Conf. Inf. Technol Big Data Artificial Intell. (ICIBA), vol. 3, May 2023, pp. 544–551.
[34] X. Li, A. Wu, and W. S. Zheng, “Adversarial open-world person re-identification,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 280–296.
[35] Y. Sun, L. Zheng, Y. Yang, Q. Tian, and S. Wang, “Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline),” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 480–496.
[36] J. Huang, W. Chen, Y. Zhang, et al., “ACINet: Adaptive context integration network for person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2021.
[37] Z. Wu, K. Yan, J. Li, et al., “Visible thermal person re-identification with deep fusion module,” IEEE Trans. Multimedia, vol. 23, pp. 1513–1524, 2021.
[38] Y. Wei, H. Fu, Z. Zheng, et al., “Temporal consistency preserving person reidentification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 3, pp. 651–664, Mar. 2022.
[39] C. Sun, Y. Yao, Y. Zhou, et al., “Deep adaptive fusion network for person re-identification,” IEEE Trans. Image Process., vol. 32, pp. 2556–2569, 2023.
[40] Z. Gong, X. Yu, S. Zhang, et al., “Disentangling cross-view correlation for multi-shot person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021.
[41] Y. Shen, Z. Yuan, Z. Wang, et al., “Temporal consistent adaptive learning for pedestrian re-identification,” IEEE Trans. Image Process., vol. 30, pp. 4000–4013, 2021.
[42] He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition (Version 1). arXiv. https://doi.org/10.48550/ARXIV.1512.03385
[43] X. Jing, R. Zuo, F. Zhang, H. Wang, and W. Ouyang, “Attention-aware compositional network for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018.
[44] C. Song, H. Yan, W. Ouyang, and W. Liang, “Mask-guided contrastive attention model for person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018.
[45] R. Zhao, W. Ouyang, and X. Wang, “Person reidentification by saliency learning,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, pp. 356–370, 2016.
[46] C. Liu, X. Chang, and Y. D. Shen, “Unity style transfer for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2020.
[2] N. V. Mahendran, “Variations of squeeze and excitation networks,” arXiv e-prints, arXiv:2304.06502v2 [cs.CV], Jul. 3, 2023.
[3] Q. Xie, Z. Lu, W. Zhou, and H. Li, “Improving person re-identification with multi-cue similarity embedding and propagation,” IEEE Trans. Multimedia, 2022.
[4] C. Gong, J. Hu, L. Zhang, W. Liu, and X. Wang, “Spatio-temporal multi-graph convolutional network for video person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023.
[5] W. Hu, L. Wang, and C. Peng, “A method for detecting anomalies in an electromagnetic environment situation using a dual-branch prediction network,” Electronics, vol. 11, no. 16, p. 2555, 2022.
[6] Z. Jiang, Y. Wang, W. Liu, L. Zhang, and J. Chen, “GLAF: Group-based local affinity feature for cross-domain person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023.
[7] X. Wang, Y. Zhang, J. Li, W. Liu, and J. Chen, “Deep multi-resolution network for person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023.
[8] X. Zhang, X. Zhang, L. Wu, C. Li, X. Chen, and X. Chen, “Domain adaptation with self-guided adaptive sampling strategy: Feature alignment for crossuser myoelectric pattern recognition,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 1374–1383, 2022.
[9] Y. Lu, M. Jiang, Z. Liu, and X. Mu, “Dual-branch adaptive attention transformer for occluded person re-identification,” Image Vis. Comput., vol. 131, p. 104633, 2023.
[10] Wencheng Qin, Baojin Huang, Pinzhong Qin, Zhiyong Huang, Daidi Zhong, Learning diverse and deep clues for person reidentification, Image and Vision Computing, Volume 126, 2022, 104551, ISSN 0262-8856, https://doi.org/10.1016/j.imavis.2022.104551.
[11] Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2021). Attention Mechanisms in Computer Vision: A Survey. arXiv. https://doi.org/10.48550/ARXIV.2111.07624
[12] L. Li, B. Chen, K. Huang, et al., “Multiscale attention graph neural networks for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023.
[13] J. Si, H. Zhang, C. G. Li, J. Kuen, X. Kong, A. C. Kot, and G. Wang, “Dual attention matching network for context-aware feature sequencebased person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 5363–5372.
[14] Z. Zhang, C. Lan, W. Zeng, X. Jin, and Z. Chen, “Relation-aware global attention for person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 3186–3195.
[15] H. Zhan, L. Zheng, Y. Wang, et al., “Pose-guided attention network for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021.
[16] A. Mohanty, B. Banerjee, and R. Velmurugan, “SSMTReID-Net: Multi-target unsupervised domain adaptation for person re-identification,” Pattern Recognit. Lett., vol. 163, pp. 40–46, 2022.
[17] Z. Pang, L. Zhao, Q. Liu, and C. Wang, “Camera invariant feature learning for unsupervised person re-identification,” IEEE Trans. Multimedia, 2022.
[18] R. Zhang, Y. Fan, H. Song, F. Wan, Y. Fu, H. Kato, and Y. Wu, “A novel retrieval-verification framework for cloth changing person re-identification,” Pattern Recognit., vol. 134, 2023.
[19] X. Wei, K. Song, W. Yang, Y. Yan, and Q. Meng, “A visible infrared clothes-changing dataset for person re-identification in natural scene,” Neurocomputing, vol. 569, p. 127110, 2024.
[20] M. Shao and H. Ling, “Dynamic curriculum learning for weakly supervised person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023.
[21] X. Yu, J. Song, Y.-Z. Song, et al., “Weakly supervised person re-identification with multi-level self-paced learning,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023.
[22] C. Shi, D. Niu, H. Gong, M. Zhang, Z. Cao, and Y. Jin, “Person reidentification lightweight network based on progressive attention mechanism,” in Proc. Int. Symp. Autonomous Syst. (ISAS), Jun. 2023, pp. 1– 6.
[23] Y. Ge, F. Zhu, X. Liu, et al., “Triplet probability learning for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020.
[24] S. Xu, Y. Hou, Z. Li, and D. Cao, “Joint face and person re-identification with bilinear transformation networks,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 9, pp. 3347–3360, Sep. 2021.
[25] Z. Zheng, X. Zhu, S. Gong, et al., “Learning to fuse local and global representations for person re-identification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 7, pp. 2429–2442, Jul. 2023.
[26] Q. Leng, M. Ye, and Q. Tian, “A survey of open-world person reidentification,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 4, pp. 1092–1108, Apr. 2019.
[27] X. Zhu, J. Zhang, J. Shi, et al., “Deep fusion of global and local representations for person re-identification,” IEEE Trans. Image Process., vol. 32, pp. 1576–1589, 2023.
[28] J. Liu, Y. Chen, X. Nie, et al., “Adaptive feature fusion network for occlusionaware person re-identification,” Pattern Recognit., 2023.
[29] X. Zhang, Z. Zhang, H. Chen, et al., “Learning to adapt template for person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021.
[30] X. Xu, S. Liu, N. Zhang, G. Xiao, and S. Wu, “Channel exchange and adversarial learning guided cross-modal person re-identification,” Knowl.-Based Syst., vol. 257, p. 109883, 2022.
[31] L. Machaca, J. Huaman, E. Clua, and J. Guerin, “TrADe Re-ID–Live person re-identification using tracking and anomaly detection,” in Proc. IEEE Int. Conf. Mach. Learn. Appl. (ICMLA), Dec. 2022, pp. 449–454.
[32] X. Zang, G. Li, W. Gao, and X. Shu, “Learning to disentangle scenes for person re-identification,” Image Vis. Comput., vol. 116, p. 104237, Dec. 2021.
[33] S. Chen, S. Chen, and Z. Lei, “FAS-ReID: Fair architecture search for person re-identification,” in Proc. IEEE Int. Conf. Inf. Technol Big Data Artificial Intell. (ICIBA), vol. 3, May 2023, pp. 544–551.
[34] X. Li, A. Wu, and W. S. Zheng, “Adversarial open-world person re-identification,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 280–296.
[35] Y. Sun, L. Zheng, Y. Yang, Q. Tian, and S. Wang, “Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline),” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 480–496.
[36] J. Huang, W. Chen, Y. Zhang, et al., “ACINet: Adaptive context integration network for person re-identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2021.
[37] Z. Wu, K. Yan, J. Li, et al., “Visible thermal person re-identification with deep fusion module,” IEEE Trans. Multimedia, vol. 23, pp. 1513–1524, 2021.
[38] Y. Wei, H. Fu, Z. Zheng, et al., “Temporal consistency preserving person reidentification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 3, pp. 651–664, Mar. 2022.
[39] C. Sun, Y. Yao, Y. Zhou, et al., “Deep adaptive fusion network for person re-identification,” IEEE Trans. Image Process., vol. 32, pp. 2556–2569, 2023.
[40] Z. Gong, X. Yu, S. Zhang, et al., “Disentangling cross-view correlation for multi-shot person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021.
[41] Y. Shen, Z. Yuan, Z. Wang, et al., “Temporal consistent adaptive learning for pedestrian re-identification,” IEEE Trans. Image Process., vol. 30, pp. 4000–4013, 2021.
[42] He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition (Version 1). arXiv. https://doi.org/10.48550/ARXIV.1512.03385
[43] X. Jing, R. Zuo, F. Zhang, H. Wang, and W. Ouyang, “Attention-aware compositional network for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018.
[44] C. Song, H. Yan, W. Ouyang, and W. Liang, “Mask-guided contrastive attention model for person reidentification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018.
[45] R. Zhao, W. Ouyang, and X. Wang, “Person reidentification by saliency learning,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, pp. 356–370, 2016.
[46] C. Liu, X. Chang, and Y. D. Shen, “Unity style transfer for person re-identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2020.