Skip to main content
SpringerLink
Log in

Choice of Activation Function in Convolutional Neural Networks for Person Re-Identification in Video Surveillance Systems

  • Published:
Programming and Computer Software Aims and scope Submit manuscript

Abstract

In this paper, we improve the accuracy of person re-identification in images obtained from distributed video surveillance systems by choosing activation functions for convolutional neural networks. The most popular activation functions used for object detection, namely, ReLU, Leaky-ReLU, PReLU, RReLU, ELU, SELU, GELU, Swish, and Mish, are analyzed based on the following metrics: Rank1, Rank5, Rank10, mAP, and training time. For feature extraction, ResNet-50, DenseNet-121, and DarkNet-53 architectures are employed. The experimental study is carried out on open datasets Market1501 and PolReID. The accuracy of person re-identification is assessed after thrice-repeated training and testing with different activation functions, neural network architectures, and datasets by averaging the values of the selected metrics.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.

Similar content being viewed by others

REFERENCES

  1. Ye, S., Bohush, R.P., Chen, H., et al., Person tracking and reidentification for multicamera indoor video surveillance systems, Pattern Recognit. Image Anal., 2020, vol. 30, pp. 827–837. https://doi.org/10.1134/S1054661820040136

    Article  Google Scholar 

  2. Porrello, A., Bergamini, L., and Calderara, S., Robust re-identification by multiple views knowledge distillation, 2020.

  3. Huang, G., Liu, Z., and Weinberger, K.Q., Densely connected convolutional networks, Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2261–2269.

  4. Wang, G., Lai, J., Huang, P., and Xie, X., Spatial-temporal person re-identification, 2019.

  5. Mao, S., Zhang, S., and Yang, M., Resolution-invariant person re-identification, 2019.

  6. Redmon, J. and Farhadi, A., YOLOv3: An incremental improvement, 2018.

  7. Nair, V. and Hinton, G.E., Rectified linear units improve restricted Boltzmann machines, Proc. ICML, 2010, pp. 807–814.

  8. Maas, A.L., Rectifier non linearities improve neural network acoustic models, Proc. ICML, 2013, vol. 30.

  9. Xu, B., Wang, N., Chen, T., and Li, M., Empirical evaluation of rectified activations in convolutional network, 2015.

  10. Clevert, D., Unterthiner, T., and Hochreiter, S., Fast and accurate deep network learning by exponential linear units (ELUs), 2016.

  11. Klambauer, G., Unterthiner, T., Mayr, A., and Hochreiter, S., Self-normalizing neural networks, 2017.

  12. Hendrycks, D. and Gimpel, K., Bridging nonlinearities and stochastic regularizers with Gaussian error linear units, 2016.

  13. Ramachandran, P., Zoph, B., and Le, Q.V., Swish: A self-gated activation function, 2017.

  14. Misra, D., Mish: A self regularized non-monotonic neural activation function, 2019.

  15. Zheng, L., Shen, L., Tian, L., Wang, Sh., Wang, J., and Tian, Q., Scalable person re-identification: A benchmark, Proc. IEEE Int. Conf. Computer Vision (ICCV), 2015, pp. 1116–1124.

  16. Ihnatsyeva, S., Bohush, R., and Ablameyko, S., Joint dataset for CNN-based person re-identification, Proc. 15th Int. Conf. Pattern Recognition and Information Processing (PRIP), Minsk, Minsk: Ob"edinennyi Inst. Probl. Inf. Nats. Akad. Nauk Belarusi, 2021, pp. 33–37.

  17. Ihnatsyeva, S. and Bohush, R., PolReID. https://github.com/SvetlanaIgn/PolReID.

  18. Bochkovskiy, A., Wang, Ch.-Y., and Liao, H.-Y.M., YOLOv4: Optimal speed and accuracy of object detection, 2020.

  19. GitHub, Person reID baseline pytorch. https://github.com/layumi/Person_reID_baseline_pytorch.

Download references

ACKNOWLEDGMENTS

This work is partially supported by the National High-end Foreign Experts Program (G2021016028L and G2021016002L) and Zhejiang Shuren University Basic Scientific Research Special Funds.

Author information

Authors and Affiliations

  1. Zhejiang Shuren University, Shuren Str. 8, Hangzhou, China

    H. Chen

  2. International Science and Technology Cooperation Base of Zhejiang Province: Remote Sensing Image Processing and Application, Shuren Str. 8, Hangzhou, China

    H. Chen

  3. Polotsk State University, ul. Blokhina 29, 211446, Novopolotsk, Belarus

    S. Ihnatsyeva & R. Bohush

  4. Belarusian State University, pr. Nezavisimosti 4, 220030, Minsk, Belarus

    S. Ablameyko

  5. United Institute of Informatics Problems, National Academy of Sciences of Belarus, ul. Surganova 6, 220012, Minsk, Belarus

    S. Ablameyko

Authors
  1. H. Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. Ihnatsyeva
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. R. Bohush
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. S. Ablameyko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to H. Chen or R. Bohush.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Translated by Yu. Kornienko

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, H., Ihnatsyeva, S., Bohush, R. et al. Choice of Activation Function in Convolutional Neural Networks for Person Re-Identification in Video Surveillance Systems. Program Comput Soft 48, 312–321 (2022). https://doi.org/10.1134/S0361768822050036

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0361768822050036

Search

Navigation