Skip to main content
Springer Nature Link
Log in

Evaluating Calibration and Robustness of Pedestrian Detectors

  • Conference paper
  • First Online:
Multimedia Communications, Services and Security (MCSS 2020)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1284))

  • 509 Accesses

Abstract

In this work the robustness and calibration of modern pedestrian detectors are evaluated. Pedestrian detection is a crucial perception component in autonomous driving and in this article its performance under different image distortions is studied. Furthermore, we provide an analysis of classification calibration of pedestrian detectors and a positive effect of using the style-transfer augmentation technique is presented. Our analysis is aimed as a step towards understanding and improving current safety-critical detection systems.

This work has been partially supported by Statutory Funds of Electronics, Telecommunications and Informatics Faculty, Gdansk University of Technology, and partially by the Polish National Centre for Research and Development (NCBR) from the European Regional Development Fund No. POIR.04.01.04-00-0089/16.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://www.kaggle.com/c/painter-by-numbers/.

References

  1. Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in ai safety. arXiv preprint arXiv:1606.06565 (2016)

  2. Braun, M., Krebs, S., Flohr, F., Gavrila, D.M.: Eurocity persons: a novel benchmark for person detection in traffic scenes. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1844–1861 (2019)

    Article  Google Scholar 

  3. Chen, K., et al.: Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)

  4. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)

    Google Scholar 

  5. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)

    Google Scholar 

  6. Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 304–311 (2009)

    Google Scholar 

  7. Feng, D., Rosenbaum, L., Glaeser, C., Timm, F., Dietmayer, K.: Can we trust you? On calibration of a probabilistic object detector for autonomous driving. arXiv preprint arXiv:1909.12358 (2019)

  8. Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of the 33nd International Conference on Machine Learning. ICML 2016, New York City, NY, USA, 19–24 June 2016, vol. 48, pp. 1050–1059 (2016)

    Google Scholar 

  9. Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: 7th International Conference on Learning Representations. ICLR 2019, New Orleans, LA, USA, 6–9 May 2019 (2019)

    Google Scholar 

  10. Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1321–1330 (2017)

    Google Scholar 

  11. Hasan, I., Liao, S., Li, J., Akram, S.U., Shao, L.: Pedestrian detection: the elephant in the room. CoRR (2020). https://arxiv.org/abs/2003.08799

  12. Hendrycks, D., Dietterich, T.G.: Benchmarking neural network robustness to common corruptions and perturbations. In: 7th International Conference on Learning Representations. ICLR 2019, New Orleans, LA, USA, 6–9 May 2019 (2019)

    Google Scholar 

  13. Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple data processing method to improve robustness and uncertainty. In: 8th International Conference on Learning Representations. ICLR 2020, Addis Ababa, Ethiopia, 26–30 April 2020 (2020)

    Google Scholar 

  14. Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501–1510 (2017)

    Google Scholar 

  15. Kohl, S., et al.: A probabilistic U-net for segmentation of ambiguous images. In: Advances in Neural Information Processing Systems, pp. 6965–6975 (2018)

    Google Scholar 

  16. Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems, pp. 6402–6413 (2017)

    Google Scholar 

  17. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  18. Liu, W., Liao, S., Ren, W., Hu, W., Yu, Y.: High-level semantic feature detection: a new perspective for pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5187–5196 (2019)

    Google Scholar 

  19. Michaelis, C., et al.: Benchmarking robustness in object detection: autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484 (2019)

  20. Platt, J., et al.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classif. 10(3), 61–74 (1999)

    Google Scholar 

  21. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)

    Google Scholar 

  22. Snoek, J., et al.: Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift. In: Advances in Neural Information Processing Systems, pp. 13969–13980 (2019)

    Google Scholar 

  23. Szegedy, C., et al.: Intriguing properties of neural networks. In: 2nd International Conference on Learning Representations. ICLR 2014, Banff, AB, Canada, 14–16 April 2014, Conference Track Proceedings (2014)

    Google Scholar 

  24. Zhang, S., Benenson, R., Schiele, B.: CityPersons: a diverse dataset for pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3221 (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Electronics, Telecommunication and Informatics Multimedia Systems Department, Gdansk University of Technology, Gdańsk, Poland

    Sebastian Cygert & Andrzej Czyżewski

Authors
  1. Sebastian Cygert
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andrzej Czyżewski
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sebastian Cygert .

Editor information

Editors and Affiliations

  1. AGH University of Science and Technology, Kraków, Poland

    Andrzej Dziech

  2. Royal Military Academy, Brussels, Belgium

    Wim Mees

  3. Gdańsk University of Technology, Gdańsk, Poland

    Andrzej Czyżewski

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Cygert, S., Czyżewski, A. (2020). Evaluating Calibration and Robustness of Pedestrian Detectors. In: Dziech, A., Mees, W., Czyżewski, A. (eds) Multimedia Communications, Services and Security. MCSS 2020. Communications in Computer and Information Science, vol 1284. Springer, Cham. https://doi.org/10.1007/978-3-030-59000-0_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-59000-0_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58999-8

  • Online ISBN: 978-3-030-59000-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics