Document Type : Original Article
Authors
Department of Electrical and Computer Engineering, University of Birjand, Iran
Abstract
Person re-identification (re-id) is one of the most critical and challenging topics in image processing and artificial intelligence. In general, person re-identification means that a person seen in the field of view of one camera can be found and tracked by other non-overlapped cameras. Low-resolution frames, high occlusion in crowded scene, and few samples for training supervised models make re-id challenging. This paper proposes a new model for person re-identification to overcome the noisy frames and extract robust features from each frame. To this end, a noise-aware system is implemented by training an auto-encoder on artificially damaged frames to overcome noise and occlusion. A model for person re-identification is implemented based on deep convolutional neural networks. Experimental results on two actual databases, CUHK01 and CUHK03, demonstrate that the proposed method performs better than state-of-the-art methods.
Keywords
Main Subjects
[1] Gou, M., Wu, Z., Rates-Borras, A., Camps, O. and Radke, R. J., 2018. A systematic evaluation and benchmark for person re-identification: Features, metrics, and datasets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(3), pp.523-536. Doi: 10.1109/TPAMI.2018.2807450
[2] Gong, S., Cristani, M., Loy, C. C., and Hospedales, T. M., 2014. The re-identification challenge. In Person re-identification. Springer, London, pp. 1-20.
[3] Yaghoubi, E., Kumar, A., and Proença, H., 2021. Sss-pr: A short survey of surveys in person re-identification. Pattern Recognition Letters, 143, pp.50-57. Doi: 10.1016/j.patrec.2020.12.017
[4] Munaro, M., Ghidoni, S., Dizmen, D. T., and Menegatti, E., 2014. A feature-based approach to people re-identification using skeleton keypoints. IEEE International Conference on Robotics and Automation (ICRA), pp. 5644-5651. Doi: 10.1109/ICRA.2014.6907689
[5] Matsukawa, T., Okabe, T., Suzuki, E., and Sato, Y., 2016. Hierarchical gaussian descriptor for person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1363-1372.
[6] Liao, S., Hu, Y., Zhu, X., and Li, S. Z., 2015. Person re-identification by local maximal occurrence representation and metric learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2197-2206.
[7] de Carvalho Prates, R. F., and Schwartz, W. R., 2015. CBRA: Color-based ranking aggregation for person re-identification. IEEE International Conference on Image Processing (ICIP), pp. 1975-1979. Doi: 10.1109/ICIP.2015.7351146
[8] Mortezaie, Z., Hassanpour, H., and Beghdadi, A., 2021. A Color-Based Re-Ranking Process for People Re-Identification: Paper ID 21. 9th European Workshop on Visual Information Processing (EUVIP), pp. 1-5. Doi: 10.1109/EUVIP50544.2021.9484056
[9] Li, W., Zhao, R., Xiao, T., and Wang, X., 2014. Deepreid: Deep filter pairing neural network for person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 152-159.
[10] Wu, G., Zhu, X., and Gong, S., 2022. Learning hybrid ranking representation for person re-identification. Pattern Recognition, 121, pp.108239. Doi: 10.1016/j.patcog.2021.108239
[11] Sezavar, A., Farsi, H., and Mohamadzadeh, S., 2022. Multi-Depth Deep Similarity Learning for Person Re-Identification. Jordan Journal of Electrical Engineering. All rights reserved-Volume, 8(3), pp. 279-287. Doi: 10.5455/jjee.204-1653115709
[12] Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P. A., 2008. Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning, pp. 1096-1103. Doi: 10.1145/1390156.1390294
[13] Tripathi, M., 2021. Facial image denoising using AutoEncoder and UNET. Heritage and Sustainable Development, 3(2), pp.89-96. Doi: 10.37868/hsd.v3i2.71
[14] Saad, O. M., and Chen, Y., 2020. Deep denoising autoencoder for seismic random noise attenuation. Geophysics, 85(4), pp. 367-376. Doi: 10.1190/geo2019-0468.1
[15] Shang, Z., Sun, L., Xia, Y., and Zhang, W., 2021. Vibration-based damage detection for bridges by deep convolutional denoising autoencoder. Structural Health Monitoring, 20(4), pp. 1880-1903. Doi: 10.1177/1475921720942836
[16] Arel, I., Rose, D. C., and Karnowski, T. P., 2010. Deep machine learning-a new frontier in artificial intelligence research [Research frontier]. IEEE Computational Intelligence Magazine, 5(4), pp. 13-18. Doi: 10.1109/MCI.2010.938364
[17] Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., and Lew, M. S., 2016. Deep learning for visual understanding: A review. Neurocomputing, 187, pp. 27-48. Doi: 10.1016/j.neucom.2015.09.116
[18] Sezavar, A., Farsi, H., and Mohamadzadeh, S., 2019. Content-based image retrieval by combining convolutional neural networks and sparse representation. Multimedia Tools and Applications, 78(15), pp. 20895-20912. Doi: 10.1007/s11042-019-7321-1
[19] Simonyan, K., and Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. ArXiv Preprint ArXiv:1409.1556. Doi: 10.48550/arXiv.1409.1556
[20] Li, W., Zhao, R., and Wang, X., 2013. Human reidentification with transferred metric learning. Asian Conference on Computer Vision. Springer, Berlin, Heidelberg. pp. 31-44. Doi: 10.1007/978-3-642-37331-2_3
[21] Li, W., Zhao, R., Xiao, T., and Wang, X., 2014. Deepreid: Deep filter pairing neural network for person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 152-159.
[22] Chen, Y. C., Zheng, W. S., Lai, J. H., and Yuen, P. C., 2016. An asymmetric distance model for cross-view feature mapping in person reidentification. IEEE Transactions on Circuits and Systems for Video Technology, 27(8), pp. 1661-1675. Doi: 10.1109/TCSVT.2016.2515309
[23] Cheng, D., Gong, Y., Zhou, S., Wang, J., and Zheng, N., 2016. Person re-identification by multi-channel parts-based cnn with improved triplet loss function. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1335-1344.
[24] Cheng, D., Gong, Y., Chang, X., Shi, W., Hauptmann, A., and Zheng, N., 2018. Deep feature learning via structured graph Laplacian embedding for person re-identification. Pattern Recognition, 82, pp. 94-104. Doi: 10.1016/j.patcog.2018.05.007
[25] Fayyaz, M., Yasmin, M., Sharif, M., Shah, J. H., Raza, M., and Iqbal, T., 2020. Person re-identification with features-based clustering and deep features. Neural Computing and Applications, 32(14), pp.10519-10540. Doi: 10.1007/s00521-019-04590-2
[26] Liu, Y., Zhang, Y., Coleman, S., Bhanu, B., and Liu, S., 2020. A new patch selection method based on parsing and saliency detection for person re-identification. Neurocomputing, 374, pp. 86-99. Doi: 10.1016/j.neucom.2019.09.073
[27] Tian, M., Yi, S., Li, H., Li, S., Zhang, X., Shi, J. and Wang, X., 2018. Eliminating background-bias for robust person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5794-5803.
[28] Zhao, H., Tian, M., Sun, S., Shao, J., Yan, J., Yi, S. and Tang, X., 2017. Spindle net: Person re-identification with human body region guided feature decomposition and fusion. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1077-1085.
[29] Matsukawa, T., Okabe, T., Suzuki, E., and Sato, Y., 2019. Hierarchical gaussian descriptors with application to person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(9), pp. 2179-2194. Doi: 10.1109/TPAMI.2019.2914686
[30] Qian, X., Fu, Y., Jiang, Y.G., Xiang, T. and Xue, X., 2017. Multi-scale deep learning architectures for person re-identification. Proceedings of the IEEE International Conference on Computer Vision, pp. 5399-5408.
)