Skip to main content
SpringerLink
Log in

Tire Surface Segmentation in Infrared Imaging with Convolutional Neural Networks and Transfer Learning

  • MATHEMATICAL THEORY OF IMAGES AND SIGNALS REPRESENTING, PROCESSING, ANALYSIS, RECOGNITION, AND UNDERSTANDING
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

It is crucial to analyze the tire under dynamic conditions to observe a performance close to realistic situations. Particularly, the temperature generated by the interaction of tire and pavement can provide useful information and understanding into how tire components can be optimized. However, in such a situation, data generation and measurement are challenging tasks. High-resolution thermal infrared imaging is a non-contact technology that transforms radiation patterns into a visible image and allows measuring the temperature changes on the surface of the tire. Therefore, the first step towards a systematic analysis of the performance of the tire is to segment the surface. To this end, we present an approach that combines traditional image processing methods with convolutional neural networks. We further investigate transfer learning techniques to improve the prediction of the proposed model on a different dataset. Our ultimate goal is to implement a robust network to segment a broad variety of tires. A segmentation accuracy >0.97 and a validation error <0.06 were achieved with transfer learning. The results have shown that our network can be extended to segment new data accurately.

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.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
Fig. 10.

Similar content being viewed by others

REFERENCES

  1. K. Anupam, S. K. Srirangam, A. Scarpas, and C. Kasbergen, “Influence of temperature on tire–pavement friction: Analyses,” Transp. Res. Rec. 2369 (1), 114–124 (2013).

    Article  Google Scholar 

  2. A. Berg, J. Ahlberg, and M. Felsberg, “A thermal object tracking benchmark,” in 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (2015), pp. 1–6.

  3. F. Büttner, M. Unterreiner, and P. Bortolussi, “An effective method to identify thermodynamic tire characteristics through driving maneuvers,” in 15. Internationales Stuttgarter Symposium (2015), pp. 921–936.

  4. F. Calabrese, M. Bäcker, and A. Gallrein, “Evaluation of different modeling approaches for the tire handling simulations – analysis and results,” in 6th International Munich Chassis Symposium (2015), pp. 749–773.

  5. A. Chaurasia and E. Culurciello, “Linknet: Exploiting encoder representations for efficient semantic segmentation,” in IEEE Visual Communications and Image Processing (VCIP) (2017), pp. 1–4.

  6. A. Corollaro, PhD Thesis (Universitá degli studi di Napoli Federico II, 2014).

  7. A. Duarte, L. Carrão, M. Espanha, T. Viana, D. Freitas, P. Bártolo, P. Faria, and H. A. Almeida, “Segmentation algorithms for thermal images,” Procedia Technol. 16, 1560–1569 (2014).

    Article  Google Scholar 

  8. J. Duchi, E. Hazan, and Y. Singer, “Adaptive subgradient methods for online learning and stochastic optimization,” J. Mach. Learn. Res. 12, 2121–2159 (2011).

    MathSciNet  MATH  Google Scholar 

  9. F. Farroni, D. Giordano, M. Russo, and F. Timpone, “TRT: Thermo racing tyre a physical model to predict the tyre temperature distribution,” Meccanica 49, 707–723 (2014).

    Article  MathSciNet  MATH  Google Scholar 

  10. A. Garcia-Garcia, S. Orts-Escolano, S. Oprea, V. Villena-Martinez, P. Martinez-Gonzalez, and J. Garcia-Rodriguez, “A survey on deep learning techniques for image and video semantic segmentation,” Appl. Soft Comput. 70, 41–65 (2018).

    Article  Google Scholar 

  11. J. Gauci, O. Falzon, C. Formosa, A. Gatt, C. Ellul, S. Mizzi, A. Mizzi, C. S. Delia, K. Cassar, N. Chockalingam, and K. P. Camilleri, “Automated region extraction from thermal images for peripheral vascular disease monitoring,” J. Healthcare Eng. 2018, 1–14 (2018).

    Article  Google Scholar 

  12. G. Gil and J. Park, Physical Handling Tire Model Incorporating Temperature and Inflation Pressure Change Effect, SAE Technical Paper 2018-01-1338 (SAE International, 2018).

  13. D. Harsh and B. Shyrokau, “Tire model with temperature effects for formula SAE vehicle,” Appl. Sci. 9 (24), 1–21 (2019).

    Article  Google Scholar 

  14. H. Iqbal, HarisIqbal88/PlotNeuralNet v1.0.0 (2018). https://doi.org/10.5281/zenodo.2526396

  15. M. Ivašić-Kos, M. Krišto, and M. Pobar, “Human detection in thermal imaging using YOLO,” in 5th International Conference on Computer and Technology Applications (ICCTA) (2019), pp. 20–24.

  16. M. Jangblad, Master’s Thesis (Uppsala Univ., 2018).

  17. C. Li, C. Xu, C. Gui, and M. D. Fox, “Distance regularized level set evolution and its application to image segmentation,” IEEE Trans. Image Process. 19 (12), 3243–3254 (2010).

    Article  MathSciNet  MATH  Google Scholar 

  18. T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in IEEE International Conference on Computer Vision (ICCV) (2017), pp. 2999–3007.

  19. C. Lugaro, M. Alirezaei, I. Konstantinou, and A. Behera, A Study on the Effect of Tire Temperature and Rolling Speed on the Vehicle Handling Response. SAE Technical Paper 2020-01-1235 (SAE International, 2020).

  20. M. P. Manda and H. S. Kim, “A fast image thresholding algorithm for infrared images based on histogram approximation and circuit theory,” Algorithms 13 (9), 207 (2020).

    Article  MathSciNet  Google Scholar 

  21. G. Mavros, “A thermo-frictional tyre model including the effect of flash temperature,” Veh. Syst. Dyn. 57 (5), 721–751 (2019).

    Article  Google Scholar 

  22. M. Mazur-Milecka and J. Ruminski, “Deep learning based thermal image segmentation for laboratory animals tracking,” Quant. InfraRed Thermogr. J. 18 (3), 159–176 (2021).

    Article  Google Scholar 

  23. F. Milletari, N. Navab, and S. Ahmadi, “V-Net: Fully convolutional neural networks for volumetric medical image segmentation,” in 2016 Fourth International Conference on 3D Vision (3DV) (2016), pp. 565–571.

  24. R. Nava, D. Fehr, F. Petry, and T. Tamisier, “Tire surface segmentation in infrared imaging with convolutional neural networks,” in ICPR International Workshops and Challenges (ICPR 2021) (2021).

    Google Scholar 

  25. Y. Qiao, Z. Wei, and Y. Zhao, “Thermal infrared pedestrian image segmentation using level set method,” Sensors 17 (8), 1811 (2017).

    Article  Google Scholar 

  26. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), pp. 779–788.

  27. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention MICCAI 2015 (2015), pp. 234–241.

  28. C. Szegedy, W. Liu, W. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), pp. 1–9.

  29. Z. Zhou, Rahman M. M. Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A nested U-net architecture for medical image segmentation,” in DLMIA/ML-CDS-2018 (2018), pp. 3–11.

Download references

Author information

Authors and Affiliations

  1. Luxembourg Institute of Science and Technology (LIST), L-4362, Esch/Alzette, Grand Duchy of Luxembourg

    Rodrigo Nava & Thomas Tamisier

  2. Goodyear Innovation Center Luxembourg, L-7750, Colmar-Berg, Luxembourg

    Duc Fehr & Frank Petry

Authors
  1. Rodrigo Nava
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Duc Fehr
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Frank Petry
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Thomas Tamisier
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Rodrigo Nava, Duc Fehr, Frank Petry or Thomas Tamisier.

Ethics declarations

COMPLIANCE WITH ETHICAL STANDARDS

This manuscript is a completely original work of its authors; it has not been published before and will not be published in other sources.

CONFLICT OF INTEREST

The content of the article does not give grounds for raising the issue of a conflict of interest.

Additional information

Rodrigo Nava holds the B.Eng., the M.Eng., and the D.Eng. from Universidad Nacional Autónoma de México, all of them with distinction. He worked as a postdoctoral fellow at the Czech Technical University in Prague from 2014 to 2017. Currently, he is a Junior Research and Technology Associate at the Luxembourg Institute of Science and Technology, LIST. His professional interests include bio-inspired image models, image quality, texture, medical imaging, microscopy image applications, and industrial imaging solutions.

Duc Fehr is an engineer in the Performance Testing Group at the Goodyear Innovation Center in Luxembourg. He received his Master’s degree in Robotics and Automation from the École Nationale Supérieure de Physique de Strasbourg in 2006. After graduating from the University of Minnesota with a PhD in computer science in 2013, he performed cancer research at the Memorial Sloan Kettering Cancer Center in New York, USA until he started working at Goodyear in 2016. Duc has authored numerous peer reviewed technical papers in reputed journals. His research is focused on image processing and machine learning.

Frank Petry is Sr. R&D associate in the Virtual Capability and Tire/Vehicle Mechanics department at the Goodyear Innovation Center in Luxembourg. He received his Diploma degree in Physics from the University of Heidelberg in 1993. With the grant support of the Max-Planck Inst. for nuclear physics, he continued his research in particle physics and graduated with a PhD from the University of Heidelberg in 1995. After two years as Lecturer in applied computer science and algebra, he started in 1997 at the Goodyear Technical Center Luxembourg in the Product Evaluation department. Frank developed new tire test and modeling methods and published several papers on tire contact mechanics and tire traction.

Thomas Tamisier holds a PhD degree in Computer Science from Telecom Paristech, France. He has been pursuing an academic and industrial career. Currently, he is with the Luxembourg Institute of Science and Technology where he leads the group “Data Processing and Statistics” of the IT for Innovative Services department, active in projects with the public and private sectors about knowledge extraction, data mining, and decision support.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nava, R., Fehr, D., Petry, F. et al. Tire Surface Segmentation in Infrared Imaging with Convolutional Neural Networks and Transfer Learning. Pattern Recognit. Image Anal. 31, 466–476 (2021). https://doi.org/10.1134/S1054661821030202

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661821030202

Keywords:

Search

Navigation