Abstract
Person re-identification based on infrared image and RGB image is a cross-modality pedestrian recognition, which is a challenging task. The traditional goal of person re-identification is to find a given person’s image from an image database, often from a single modality database. In real applications, there are often multiple modalities of data. Traditional single modality tasks have limitations. Cross-modality person re-identification needs to extract features from RGB and infrared images. In our work, we take advantage of both global and local features. First, we use a dual-path VIT structure to extract features from RGB images and infrared images, respectively. Secondly, we cut the local features in the spatial direction and input the shared VIT layer to learn the local features. The loss function consists of Identity loss, Triplet loss, and Center loss. The model can capture shared features between modality and improve cross-modality similarity. Finally, we performed experiments on two datasets, SYSU-MM01 and RegDB, and compared them with other methods in recent studies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984 (2016)
Ye, M.: Deep learning for person re-identification: a survey and outlook (2020)
Gheissari, N., Sebastian, T.B., Hartley, R.: Person reidentification using spatiotemporal appearance. In: 2006 IEEE Computer Society Conference on IEEE Computer Vision and Pattern Recognition, pp. 1528–1535 (2006)
Bazzani, L., Cristani, M., Perina, A., et al.: Multiple-shot person re-identification by HPE signature. In: 2010 20th International Conference on Pattern Recognition, pp. 1413–1416. IEEE (2010)
Farenzena, M., Bazzani, L., Perina, A., et al.: Person re-identification by symmetry-driven accumulation of local features. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2360–2367. IEEE (2010)
Wu, Y., Qin, X., Pan, Y., et al.: Convolution neural network based transfer learning for classifition of floers. In: 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP), pp. 562–566. IEEE (2018)
Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Pp. 4353–4361 (2015)
Yuan, C., Wu, Y., Qin, X., et al.: An effective image classification method for shallow densely connected convolution networks through squeezing and splitting techniques. Appl. Intell. 49(10), 3570–3586 (2019)
Liu, C., Gong, S., Loy, C.C., Lin, X.: Person re-identification: what features are important? In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 391–401. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33863-2_39
Wu, Y., Zhang, K., Wu, D., Wu, Y., et al.: Person reidentification by multiscale feature representation learning with random batch feature mask. IEEE Trans. Cogn. Dev. Syst. 13(4), 865–874 (2021)
Wu, Y., et al.: Position Attention-Guided Learning for Infrared-Visible Person Re-identification. In: Huang, De-Shuang., Bevilacqua, Vitoantonio, Hussain, Abir (eds.) ICIC 2020. LNCS, vol. 12463, pp. 387–397. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60799-9_34
Dai, P., Ji, R., Wang, H., Wu, Q., Huang, Y.: Cross modality person re-identification with generative adversarial training. In: IJCAI, pp. 677–683 (2018)
Wu, A.: RGB infrared cross modality person re identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5380–5389 (2017)
Wang, G., Zhang, T., Cheng, J., Liu, S., Yang, Y., Hou, Z.: RGB-infrared cross-modality person reidentification via joint pixel and feature alignment. In: ICCV, pp. 3622–3631 (2019)
He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: TransReID: transformer-based object reidentification. CoRR, abs/2102.04378 (2021)
Wu, A., Zheng, W.S., Yu, H.X., et al.: RGB-infrared cross-modality person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5380–5389 (2017)
Ye, M., Lan, X., Li, J., et al.: Hierarchical discriminative learning for visible thermal person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)
Dai, P., Ji, R., Wang, H., et al.: Cross-modality person re-identification with generative adversarial training. In: IJCAI, vol. 1, p. 2 (2018)
Liu, H., Cheng, J., Wang, W., et al.: Enhancing the discriminative feature learning for visible-thermal cross-modality person re-identification. Neurocomputing 398, 11–19 (2020)
Zhang, Z., Zhang, H., Liu, S., et al.: Part-guided graph convolution networks for person re-identification. Pattern Recogn. 120, 108155 (2021)
Vaswani, A., et al.: 2017. Attention is all you need. In NIPS, pp. 5998–6008 (2017)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In ICLR (2021)
Dat, T.N., Hyung, G.H., Ki, W.K.: Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors 17(3), 605 (2017)
Ye, M., Lan, X., Li, J.: Hierarchical discriminative learning for visible thermal person re identification. In: Thirty Second AAAI Conference on Artificial Intelligence (2018)
Ye, M., Wang, Z., Lan, X., Yuen, P.C.: Visible thermal person re-identification via dualconstrained top-ranking. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 1092–1099 (2018)
Wang, Z., Wang, Z., Zheng, Y.: Learning to reduce dual level discrepancy for infrared visible person re identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 618–626 (2019)
Jiang, J., et al.: A cross-modal multi-granularity attention network for RGB-IR person re-identification. Neurocomputing, p. 406 (2020)
Wang, G.-A., Zhang, T., Yang, Y.: Cross-modality paired images generation for RGB–infrared person re–identification. In: Thirty-Fourth AAAI Conference on Artificial Intelligence (2020)
Li, D., Wei, X., Hong, X., Gong, Y.: Infrared-visible cross-modal person re-identification with an X modality. In: Thirty-Fourth AAAI Conference on Artificial Intelligence (2020)
Ye, M., Lan, X., Leng, Q., Shen, J.: Cross-modality person reidentification via modality-aware collaborative ensemble learning. IEEE Trans. Image Process. 29, 9387–9399 (2020)
Hao, Y., Wang, N., Gao, X., Li, J., Wang, X.: Dual-alignment feature embedding for cross-modality person re-identification. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 57–65 (2019)
Tian, X., Zhang, Z., Lin, S., et al.: Farewell to mutual information: variational distillation for cross-modal person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1522–1531 (2021)
Tian, X., et al.: Farewell to mutual information: variational distillation for cross-modal person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1522–1531 (2021)
Chen, Y., et al.: Neural feature search for RGB-infrared person reidentification. arXiv preprint arXiv:2104.02366 (2021)
Huang, J., Huang, D.S.: Deep reinforcement learning based trajectory pricing on ride-hailing platforms. ACM Trans. Intell. Syst. Technol. vol. 13, no. 3, Article 41 (2022)
Wu, Y., et al.: Person reidentification by multiscale feature representation learning with random batch feature mask. IEEE Trans. Cogn. Dev. Syst. 13(4), 865–874 (2021)
Wu, D., Wang, C., Wu, Y., Wang, Q.-C., Huang, D.S.: Attention deep model with multi-scale deep supervision for person re-identification. IEEE Trans. Emerg. Top. Comput. Intell. 5(1), 70–78 (2021)
Liang, X., Wu, D., Huang, D.S.: Image co-segmentation via locally biased discriminative clustering. IEEE Trans. Knowl. Data Eng. 31(11), 2228–2233 (2019)
Wu, D., et al.: Deep learning based methods for person re-identification: a comprehensive review. Neurocomputing 337, 354–371 (2019)
Wu, D., et al.: Random occlusion-recovery for person re-identification. J. Imaging Sci. Technol. 63(3), 30405-1–30405-9(9) (2019)
Li, B., Fan, Z.T., Zhang, X.L., Huang, D.S.: Robust dimensionality reduction via feature space to feature space distance metric learning. Neural Netw. 112(4), 1–14 (2019)
Wu, D., et al.: Omnidirectional feature learning for person re-identification. IEEE Access 7, 28402–28411 (2019)
Wu, D., Zheng, S.-J., Yuan, C.-A., Huang, D.S.: A deep model with combined losses for person re-identification. Cogn. Syst. Res. 54, 74–82 (2019)
Wu, D., Zheng, S.-J., Bao, W.-Z., Zhang, X.-P., Yuan, C.-A., Huang, D.S.: A novel deep model with multi-loss and efficient training for person re-identification. Neurocomputing 324, 69–76 (2019)
Peng, C., Zou, L., Huang, D.S.: Discovery of relationships between long non-coding RNAs and genes in human diseases based on tensor completion. IEEE Access 6, 59152–59162 (2018)
Yang, B., Bao, W., Huang, D.S., Chen, Y.: Inference of large-scale time-delayed gene regulatory network with parallel mapReduce cloud platform. Sci. Rep. 8, 17787 (2018)
Shen, Z., Bao, W.-Z., Huang, D.S.: Recurrent neural network for predicting transcription factor binding sites. Sci. Rep. 8, 15270 (2018)
Liu, B., Weng, F., Huang, D.S., Chou, K.-C.: HSCVFNT: inference of time-delayed gene regulatory network based on complex-valued flexible neural tree model. Int. J. Mol. Sci. 19(10), 3178 (2018)
Zhang, H., Zhu, L., Huang, D.S.: DiscMLA: an efficient discriminative motif learning algorithm over high-throughput datasets. IEEE/ACM Trans. Comput. Biol. Bioinf. 15(6), 1810–1820 (2018)
Acknowledgements
This work was supported by the grant of National Key R&D Program of China (No. 2018AAA0100100 & 2018YFA0902600) and partly supported by National Natural Science Foundation of China (Grant nos. 61732012, 62002266, 61932008, and 62073231), and Introduction Plan of High-end Foreign Experts (Grant no. G2021033002L) and, respectively, supported by the Key Project of Science and Technology of Guangxi (Grant no. 2021AB20147), Guangxi Natural Science Foundation (Grant nos. 2021JJA170204 & 2021JJA170199) and Guangxi Science and Technology Base and Talents Special Project (Grant nos. 2021AC19354 & 2021AC19394).
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
Pu, Q., Yuan, C., Wu, H., Zhao, X. (2022). Local Feature for Visible-Thermal PReID Based on Transformer. In: Huang, DS., Jo, KH., Jing, J., Premaratne, P., Bevilacqua, V., Hussain, A. (eds) Intelligent Computing Theories and Application. ICIC 2022. Lecture Notes in Computer Science, vol 13393. Springer, Cham. https://doi.org/10.1007/978-3-031-13870-6_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-13870-6_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13869-0
Online ISBN: 978-3-031-13870-6
eBook Packages: Computer ScienceComputer Science (R0)