Advertisement

Low-Rank Matrix Recovery for Traffic Sign Recognition in Image Sequences

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 215)

Abstract

We consider the problem of traffic sign recognition in image sequences. In many cases, image sequences of traffic signs can be collected from consecutive videos and these images have high correlation with each other. While traditional traffic sign recognition approaches focus on how to extract better features and design more powerful classifiers, most of these methods neglected this correlation. In this paper, we introduce the low-rank matrix recovery model to exploit the correlation among images with similar appearances to enhance feature representation. By recovering the underlying low-rank matrix from the original feature matrix consists of feature vectors of image sequences, we are able to attenuate the influence of corruption, such as noise and motion blur. Experiments are conducted on GTSRB dataset to evaluate our method, and noticeable performance gain is observed by using low-rank matrix recovered from original matrix. We obtain very impressive results on several super-class accuracy while get comparable performance with state-of-the-art results on global accuracy.

Keywords

Computer vision Traffic sign recognition Low rank matrix recovery 

Notes

Acknowledgments

This work was jointly supported by the National Key Project for Basic Research of China (Grant No: 2013CB329403), the National Natural Science Foundation of China (Grants No.90820304, 61075027, 91120011), the Tsinghua Self-innovation Project (Grant No:20111081111), and the Tsinghua National Laboratory for Information Science and Technology (TNList) Cross-discipline Foundation (No. 042003023).

References

  1. 1.
    Paclik P (1999) Road sign recognition survey. http://euler.fd.cvut.cz/research/rs2/files/skoda-rs-survey.html
  2. 2.
    Kardkovacs ZT, Paroczi Z, Varga E, Siegler A, Lucz P (2011) Real-time traffic sign recognition system. In: proceedings of second international conference on cognitive infocommunications(CogInfoCom), pp 1–5Google Scholar
  3. 3.
    Maldonado-Bascon S, Lafuente-Arroyo S, Gil-Jimenez P, Gomez-Moreno H, Lopez-Ferreras F (2007) Road-sign detection and recognition based on support vector machines. IEEE Trans Intell Trans Syst 8(2):264–278CrossRefGoogle Scholar
  4. 4.
    Ruta A, Li Y, Liu X (2010) Robust class similarity measure for traffic sign recognition. IEEE Trans Intell Trans Syst 11(4):846–855CrossRefGoogle Scholar
  5. 5.
    Stallkamp J, Schlipsing M, Salmen J, Igel C, Man versus computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw (in press)Google Scholar
  6. 6.
    Ciresan D, Meier U, Mascim J, Schmidhuber J (2011) A committee of neural networks for traffic sign classification. In: Proceedings of international joint conference on neural networks (IJCNN), pp 1918–1921Google Scholar
  7. 7.
    Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks. In: Proceedings of the international joint conferece on neural networks (IJCNN), pp 2809–2813Google Scholar
  8. 8.
    Zaklouta F, Stanciulescu B, Hamdoun O (2011) Traffic sign classification using k-d trees and random forests. In: Proceedings of the international joint conference on neural networks (IJCNN), pp 2151–2155Google Scholar
  9. 9.
    Bahlmann C, Zhu Y, Ramesh V, Pellkofer M, Koehler T (2005) A system for traffic sign detection, tracking, and recognition using color, shape, and motion information. In: Proceedings of IEEE intelligent vehicles symposium, pp 255–260Google Scholar
  10. 10.
    Ruta A, Li Y, Liu X (2008) Detection, tracking and recognition of traffic signs from video input. In: Proceedings of international IEEE conference on intelligent transportation systems, School of Information Systems, pp 55–60Google Scholar
  11. 11.
    Ruta A, Li Y, Liu X (2010) Real-time traffic sign recognition from video by class-specific discriminative features. Pattern Recognit 43(1):416–430CrossRefMATHGoogle Scholar
  12. 12.
    Moutarde F, Bargeton A, Herbin A, Chanussot L (2007) Robust on-vehicle real-time visual detection of American and European speed limit signs, with a modular traffic signs recognition system. In: Proceedings of IEEE intelligent vehicles symposium, pp 1122–1126Google Scholar
  13. 13.
    Lafuente-Arroyo S, Maldonado-Bascon S, Gil-Jimenez P, Acevedo-Rodriguez J, Lopez-Sastre RJ (2007) A tracking system for automated inventory of road signs. In: Proceedings of the IEEE intelligent vehicles symposium, pp 166–171Google Scholar
  14. 14.
    Zhou X, Yang C, Yu W, Moving object detection by detecting contiguous outliers in the low-rank representation. IEEE Trans Pattern Anal Mach Intell (in press)Google Scholar
  15. 15.
    Cui X, Huang J, Zhang S, Metaxas D (2012) Background subtraction using low rank and group sparsity constraints. In: Proceedings of the European conference on computer vision (ECCV)Google Scholar
  16. 16.
    Shen X, Wu Y (2012) A unified approach to salient object detection via low rank matrix recovery. In: Proceedings of the computer vision and pattern recognition (CVPR)Google Scholar
  17. 17.
    Yan J, Zhu M, Liu H, Liu Y (2010) Visual saliency detection via sparsity pursuit. IEEE Signal Process Lett 17(8):739–742CrossRefGoogle Scholar
  18. 18.
    Peng Y, Ganesh A, Wright J, Ma Y (2010) Robust alignment by sparse and low-rank decomposition for linearly correlated images. In: Proceedings of the computer vision and pattern recognition (CVPR)Google Scholar
  19. 19.
    Fazel M, Hindi H, Boyd SP (2001) A rank minimization heuristic with application to minimum order system approximation. In: Proceedings of the american control conference (ACC), pp 4734–4739Google Scholar
  20. 20.
    Candes E, Li X, Ma Y, Wright J (2011) Robust principal component analysis? J ACM 58:1–37Google Scholar
  21. 21.
  22. 22.
    Lin Z, Chen M, Ma Y (2009) The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. Technical report, UIUC UILU-ENG-09-2215, arXiv:1009.5055Google Scholar
  23. 23.
    Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ (2008) LIBLINEAR: a library for large linear classification. J Mach Learn Res 9:1871–1874Google Scholar
  24. 24.
    Stallkamp J, Schlipsing M, Salmen J, Igel C (2011) The German traffic sign recognition benchmark: a multi-class classification competition. In: Proceedings of the international joint conference on neural networks (IJCNN), pp 1453–1460Google Scholar
  25. 25.
    Ciresan DC, Meier U, Gambardella LM, Schmidhuber J (2010) Deep, big, simple neural nets for handwritten digit recognition. Neural Comput 22:3207–3220Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Department of Computer Science and TechnologyTsinghua UniversityBeijingChina
  2. 2.State Key Laboratory of Intelligent Technology and SystemsBeijingChina
  3. 3.Tsinghua National Laboratory for Information Science and TechnologyBeijingChina

Personalised recommendations