Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Lightweight Regression Model with Prediction Interval Estimation for Computer Vision-based Winter Road Surface Condition Monitoring (2310.00923v2)

Published 2 Oct 2023 in cs.CV

Abstract: Winter conditions pose several challenges for automated driving applications. A key challenge during winter is accurate assessment of road surface condition, as its impact on friction is a critical parameter for safely and reliably controlling a vehicle. This paper proposes a deep learning regression model, SIWNet, capable of estimating road surface friction properties from camera images. SIWNet extends state of the art by including an uncertainty estimation mechanism in the architecture. This is achieved by including an additional head in the network, which estimates a prediction interval. The prediction interval head is trained with a maximum likelihood loss function. The model was trained and tested with the SeeingThroughFog dataset, which features corresponding road friction sensor readings and images from an instrumented vehicle. Acquired results highlight the functionality of the prediction interval estimation of SIWNet, while the network also achieved similar point estimate accuracy as the previous state of the art. Furthermore, the SIWNet architecture is several times more lightweight than the previously applied state-of-the-art model, resulting in more practical and efficient deployment.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. C.-G. Wallman and H. Åström, “Friction measurement methods and the correlation between road friction and traffic safety: A literature review,” 2001.
  2. M. Acosta, S. Kanarachos, and M. Blundell, “Road friction virtual sensing: A review of estimation techniques with emphasis on low excitation approaches,” Applied Sciences, vol. 7, no. 12, p. 1230, 2017.
  3. Y. Ma, M. Wang, Q. Feng, Z. He, and M. Tian, “Current non-contact road surface condition detection schemes and technical challenges,” Sensors, vol. 22, no. 24, p. 9583, 2022.
  4. D. Vosahlik, J. Cech, T. Hanis, A. Konopisky, T. Rurtle, J. Svancar, and T. Twardzik, “Self-supervised learning of camera-based drivable surface friction,” in 2021 IEEE International Intelligent Transportation Systems Conference (ITSC).   IEEE, 2021, pp. 2773–2780.
  5. M. Bijelic, T. Gruber, F. Mannan, F. Kraus, W. Ritter, K. Dietmayer, and F. Heide, “Seeing through fog without seeing fog: Deep multimodal sensor fusion in unseen adverse weather,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11 682–11 692.
  6. F. Gustafsson, “Slip-based tire-road friction estimation,” Automatica, vol. 33, no. 6, pp. 1087–1099, 1997.
  7. D. Pavković, J. Deur, J. Asgari, and D. Hrovat, “Experimental analysis of potentials for tire friction estimation in low-slip operating mode,” SAE Transactions, pp. 369–380, 2006.
  8. J. Alonso, J. López, I. Pavón, M. Recuero, C. Asensio, G. Arcas, and A. Bravo, “On-board wet road surface identification using tyre/road noise and support vector machines,” Applied acoustics, vol. 76, pp. 407–415, 2014.
  9. V. V. Viikari, T. Varpula, and M. Kantanen, “Road-condition recognition using 24-ghz automotive radar,” IEEE transactions on intelligent transportation systems, vol. 10, no. 4, pp. 639–648, 2009.
  10. P. Jonsson and M. Riehm, “Infrared thermometry in winter road maintenance,” Journal of Atmospheric and Oceanic Technology, vol. 29, no. 6, pp. 846–856, 2012.
  11. J. Casselgren and M. Sjödahl, “Polarization resolved classification of winter road condition in the near-infrared region,” Applied optics, vol. 51, no. 15, pp. 3036–3045, 2012.
  12. Y. Wu, F. Liu, L. Guan, and X. Yang, “A survey of vision-based road parameter estimating methods,” in Intelligent Computing Methodologies: 16th International Conference, ICIC 2020, Bari, Italy, October 2–5, 2020, Proceedings, Part III 16.   Springer, 2020, pp. 314–325.
  13. M. Nolte, N. Kister, and M. Maurer, “Assessment of deep convolutional neural networks for road surface classification,” in 2018 21st International Conference on Intelligent Transportation Systems (ITSC).   IEEE, 2018, pp. 381–386.
  14. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  15. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818–2826.
  16. E. Šabanovič, V. Žuraulis, O. Prentkovskis, and V. Skrickij, “Identification of road-surface type using deep neural networks for friction coefficient estimation,” Sensors, vol. 20, no. 3, p. 612, 2020.
  17. Z.-h. Wang, S.-b. Wang, L.-r. Yan, and Y. Yuan, “Road surface state recognition based on semantic segmentation,” Journal of Highway and Transportation Research and Development (English Edition), vol. 15, no. 2, pp. 88–94, 2021.
  18. K. Cordes, C. Reinders, P. Hindricks, J. Lammers, B. Rosenhahn, and H. Broszio, “Roadsaw: A large-scale dataset for camera-based road surface and wetness estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4440–4449.
  19. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510–4520.
  20. J. Van Amersfoort, L. Smith, Y. W. Teh, and Y. Gal, “Uncertainty estimation using a single deep deterministic neural network,” in International conference on machine learning.   PMLR, 2020, pp. 9690–9700.
  21. S. Roychowdhury, M. Zhao, A. Wallin, N. Ohlsson, and M. Jonasson, “Machine learning models for road surface and friction estimation using front-camera images,” in 2018 International Joint Conference on Neural Networks (IJCNN).   IEEE, 2018, pp. 1–8.
  22. Z. Du, A. Skar, M. Pettinari, and X. Zhu, “Pavement friction evaluation based on vehicle dynamics and vision data using a multi-feature fusion network,” Transportation Research Record, p. 03611981231165029, 2023.
  23. M. Abdar, F. Pourpanah, S. Hussain, D. Rezazadegan, L. Liu, M. Ghavamzadeh, P. Fieguth, X. Cao, A. Khosravi, U. R. Acharya et al., “A review of uncertainty quantification in deep learning: Techniques, applications and challenges,” Information fusion, vol. 76, pp. 243–297, 2021.
  24. N. Dewolf, B. D. Baets, and W. Waegeman, “Valid prediction intervals for regression problems,” Artificial Intelligence Review, vol. 56, no. 1, pp. 577–613, 2023.
  25. D. Nix and A. Weigend, “Estimating the mean and variance of the target probability distribution,” in Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN’94), vol. 1, 1994, pp. 55–60 vol.1.
  26. A. Khosravi, S. Nahavandi, D. Creighton, and A. F. Atiya, “Lower upper bound estimation method for construction of neural network-based prediction intervals,” IEEE transactions on neural networks, vol. 22, no. 3, pp. 337–346, 2010.
  27. C. P. Robert, “Simulation of truncated normal variables,” Statistics and computing, vol. 5, pp. 121–125, 1995.
  28. K. He, X. Zhang, S. Ren, and J. Sun, “Identity mappings in deep residual networks,” in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14.   Springer, 2016, pp. 630–645.
  29. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
  30. M. Tan and Q. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” in International conference on machine learning.   PMLR, 2019, pp. 6105–6114.
  31. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, 2019.
  32. T. Gneiting and A. E. Raftery, “Strictly proper scoring rules, prediction, and estimation,” Journal of the American statistical Association, vol. 102, no. 477, pp. 359–378, 2007.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now