Abstract
Person re-identification, aiming to identify images of the same person from non-overlapping camera views in different places, has attracted a lot of interests in intelligent video surveillance. As one of the newly emerging applications, deep learning has been incorporated into the feature representation of person re-identification. However, the existing deep feature learning methods are difficult to generate the robust and discriminative features since they use a fixed scale training and thus fail to adapt to diversitified scales for the same persons under realistic conditions. In this paper, a multi-scale triplet deep convolutional neural network (MST-CNN) is proposed to produce multi-scale features for person re-identification. The proposed MST-CNN consists of three sub-CNNs with respect to full scale, top scale (top part of persons) and half scale of the person images, respectively. In addition, these complementary scale-specific features are then passed to the l2-normalization layer for feature selection to obtain a more robust person descriptor. Experimental results on two public person re-identification datasets, i.e., CUHK-01 and PRID450s, demonstrate that our proposed MVT-CNN method outperforms most of the existing feature learning algorithms by 8%–10% at rank@1 in term of the cumulative matching curve (CMC) criterion.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, J., Wang, Z., Gao, C., Sang, N., Huang, R.: DeepList: learning deep features with adaptive listwise constraint for person reidentification. IEEE Trans. Circuits Syst. Video Technol. 27, 513–524 (2017)
Wang, Z., Hu, R., Chen, C., Yu, Y., Jiang, J., Liang, C., Satoh, S.: Person reidentification via discrepancy matrix and matrix metric. IEEE Trans. Cybern. (2017). https://doi.org/10.1109/TCYB.2017.2755044
Wang, X., Zhang, T., Tretter, D.R., Lin, Q.: Personal clothing retrieval on photo collections by color and attributes. IEEE Trans. Multimedia 15, 2035–2045 (2013)
Wang, J., Wang, Z., Liang, C., Gao, C., Sang, N.: Equidistance constrained metric learning for person re-identification. Pattern Recogn. (2017). https://doi.org/10.1016/j.patcog.2017.09.014
Ye, M., Liang, C., Yu, Y., Wang, Z., Leng, Q., Xiao, C., Chen, J., Hu, R.: Person reidentification via ranking aggregation of similarity pulling and dissimilarity pushing. IEEE Trans. Multimedia 13, 2553–2566 (2016)
Vezzani, R., Baltieri, D., Cucchiara, R.: People reidentification in surveillance and forensics: a survey. ACM Comput. Surv. 46, 1–37 (2013)
Ye, M., Andy, M.J., Zheng, L., Li, J.W., Yuen, P.C.: Dynamic label graph matching for unsupervised video re-identification. In: International Conference on Computer Vision, pp. 11–19 (2017)
Liang, C., Huang, B., Hu, R.: A unsupervised person re-identification method using model based representation and ranking. In: ACM International Conference on Multimedia, pp. 771–774 (2015)
Figueira, D., Bazzani, L., Minh, H.Q.: Semi-supervised multi-feature learning for person re-identification. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 111–116 (2013)
Xiong, M.F., Chen, J., Wang, Z., Wang, Z.Y., Hu, R., Liang, C., Shi, D.: Person re-identification via multiple coarse-to-fine deep metrics. In: IOS Press European Conference on Artificial Intelligence, pp. 355–362 (2016)
Dong, Y., Zhen, L., Liao, S.C., Li, S.: Deep metric learning for person re-identification. In: IEEE International Conference Pattern Recognition, pp. 34–39 (2014)
Ahmed, E., Jones, M., Marks, T.K.: An improved deep learning architecture for person re-identification. In: IEEE Computer Vision and Pattern Recognition, pp. 3908–3916 (2015)
Xiao, T., Li, H., Ouyang, W., Wang, X.: Learning deep feature representations with domain guided dropout for person re-identification, pp. 1249–1258 (2016)
Wang, Z., Hu, R., Liang, C., Yu, Y.: Zero-shot person reidentification via cross-view consistency. IEEE Trans. Multimedia 18, 260–272 (2016)
He, Y., Mao, Y., Chen, W., Chen, Y.: Nonlinear metric learning with kernel density estimation. IEEE Trans. Knowl. Data Eng. 27, 1602–1614 (2015)
Wang, J., Sang, N., Wang, Z., Gao, C.: Similarity learning with top-heavy ranking loss for person re-identification. IEEE Sig. Process. Lett. 23, 1–15 (2015)
Gong, S., Cristani, M., Yan, S., Chen, C.L.: Person re-identification. Vis. Anal. Behav. 42, 301–313 (2013)
Gens, R., Domingos, P.: Discriminative learning of sum-product networks. In: MIT Press Advances in Neural Information Processing Systems, pp. 3239–3247 (2012)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: MIT Press Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Wu, S., Chen, Y.C., Li, X., Wu, A.C., You, J.J., Zheng, W.S.: An enhanced deep feature representation for person re-identification. In: IEEE Winter Conference on Applications of Computer Vision, pp. 1–8 (2016)
Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354–370. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_22
Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: IEEE International Workshop on Performance Evaluation for Tracking and Surveillance, pp. 309–314 (2007)
Li, W., Wang, X.: Locally aligned feature transforms across views. In: IEEE Computer Vision and Pattern Recognition, pp. 3594–3601 (2013)
Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 91–102. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21227-7_9
Ding, S., Lin, L., Wang, G.: Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn. 48, 2993–3003 (2015)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)
Liu, H., Feng, J., Qi, M.: End-to-end comparative attention networks for person re-identification. IEEE Trans. Image Process. 26, 3492–3506 (2017)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)
Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: deep filter pairing neural network for person re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 152–159 (2014)
Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10, 207–244 (2009)
Dikmen, M., Akbas, E., Huang, T.S., Ahuja, N.: Pedestrian recognition with a learned metric. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6495, pp. 501–512. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-19282-1_40
Pedagadi, S., Orwell, J., Velastin, S., Boghossian, B.: Local fisher discriminant analysis for pedestrian re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3318–3325 (2013)
Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: International Conference on Machine Learning, pp. 209–216 (2007)
Acknowledgments
This work was supported by the National High Technology Research and Development Program of China (No.2015AA016306), the Natural Science Foundation of Jiangsu Province (No. BK20161563), EU-FP7-QUICK project under Grant Agreement (No. PIRSES-GA-2013-612652), National Nature Science Foundation of China (U1611461, 61231015, 61772380, 61671336, 61671332), the Technology Research Program of Ministry of Public Security (No. 2016JSYJA12), Hubei Province Technological Innovation Major Project (No. 2016AAA015). National Key Research and Development Program of China (No.2016YFB0100901), the Fundamental Research Funds for the Central Universities (2042016gf0033), the Basic Research Program of Shenzhen City (JCYJ20170306171431656).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Xiong, M., Chen, J., Wang, Z., Liang, C., Lei, B., Hu, R. (2018). A Multi-scale Triplet Deep Convolutional Neural Network for Person Re-identification. In: Satoh, S. (eds) Image and Video Technology. PSIVT 2017. Lecture Notes in Computer Science(), vol 10799. Springer, Cham. https://doi.org/10.1007/978-3-319-92753-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-92753-4_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92752-7
Online ISBN: 978-3-319-92753-4
eBook Packages: Computer ScienceComputer Science (R0)