Traffic sign recognition is a very important function in automatic driving assistance systems (ADAS). This study addresses the design and implementation of a vision-based ADAS based on an image-based speed-limit sign (SLS) recognition algorithm, which can automatically detect and recognise SLS on the road in real-time. To improve the recognition rate of SLS having different orientations and scales in the image, this study also presents a new sign content description algorithm, which describes the detected road sign using centroid-to-contour (CtC) distances of the extracted sign content. The proposed CtC descriptor is robust to translation, rotation and scale changes of the SLS in the image. This advantage improves the recognition accuracy of a support vector machine classifier trained using a large database of traffic signs. The proposed SLS recognition method had been implemented on two different embedded platforms, each of them equipped with an ARM-based Quad-Core CPU running Android 4.4 operating system. Experimental results validate that the proposed method not only provides a high recognition rate, but also achieves real-time performance up to 30 frames per second for processing 1280 × 720 video streams running on a commercial ARM-based smartphone.

References

1. 1)
  - 9. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, San Diego, CA, USA, 2005, pp. 886–893.
2. 2)
  - 7. Jin, J., Fu, K., Zhang, C.: ‘Traffic sign recognition with hinge loss trained convolutional neural networks’, IEEE Trans. Intell. Transp. Syst., 2014, 15, (4), pp. 1991–2000.
3. 3)
  - 34. Belgium traffic sign dataset webpage. Available at http://www.vision.ee.ethz.ch/~timofter/traffic_signs/.
4. 4)
  - 22. Otsu, N.: ‘A threshold selection method from gray-level histograms’, IEEE Trans. Syst. Man Cybern., 1979, 9, (1), pp. 62–66.
5. 5)
  - 1. García-Garrido, M.Á., Sotelo, M.Á., Martín-Gorostiza, E.: ‘Fast road sign detection using Hough transform for assisted driving of road vehicles’. Proc. of 10th Int. Conf. on Computer Aided Systems Theory, Las Palmas de Gran Canaria, Spain, 2005, pp. 543–548.
6. 6)
  - 17. Lafuente-Arroyo, S., Gil-Jimenez, P., Maldonado-Bascon, R., et al: ‘Traffic sign shape classification evaluation I: SVM using distance to borders’. Proc. of IEEE Intelligent Vehicles Symp., Nevada, USA, 2005, pp. 557–562.
7. 7)
  - 26. Hossain, M.S., Hasan, M.M., Ali, M.A., et al: ‘Automatic detection and classification of traffic signs’. IEEE Conf. on Robotics Automation and Mechatonics, Singapore, 2010, pp. 286–291.
8. 8)
  - 2. Wu, G., Liu, W., Xie, X., et al: ‘A shape detection method based on the radial symmetry nature and direction-discriminated voting’. IEEE Int. Conf. on Image Processing, San Antonio, USA, 2007, pp. VI-169–VI-172.
9. 9)
  - 3. Mgelmose, A., Trivedi, M.M., Moeslund, T.B.: ‘Vision-based traffic sign detection and analysis for intelligent driver assistance systems: Perspectives and survey’, IEEE Trans. Intell. Transp. Syst., 2012, 13, (4), pp. 1484–1497.
10. 10)
  - 6. Salhi, A., Minaoui, B., Fakir, M.: ‘Robust automatic traffic signs recognition using fast polygonal approximation of digital curves and neural network’. Int. Conf. on Multimedia Computing and Systems, Marrakech, Morocco, 2014, pp. 433–437.
11. 11)
  - 32. ASUS PadFone S (PF500KL) specifications. Available at https://www.asus.com/Phone/PadFone_S_PF500KL/specifications/.
12. 12)
  - 13. Waite, S., Oruklu, E.: ‘FPGA-based traffic sign recognition for advanced driver assistance systems’, J. Transp. Technol., 2013, 3, (1), pp. 1–16.
13. 13)
  - 28. Ludwig, O., Delgado, D., Goncalves, V., et al: ‘Trainable classifier-fusion schemes: An application to pedestrian detection’. 12th Int. IEEE Conf. on Intelligent Transportation Systems, St. Louis, 2009, pp. 432–437.
14. 14)
  - 11. Mathias, M., Timofte, R., Benenson, R., et al: ‘Traffic sign recognition – How far are we from the solution?’ Int. Joint Conf. on Neural Networks, Dallas, TX, USA, 2013, pp. 1–8.
15. 15)
  - 27. Gao, H., Liu, X., Liu, Z., et al: ‘Investigation on traffic signs recognition based on BP neural network and invariant moments’, Adv. Future Comput. Control Syst., 2012, 1, AISC 159, pp. 157–162.
16. 16)
  - 24. Hu, M.-K.: ‘Visual pattern recognition by moment invariants’, IRE Trans. Inf. Theory, 1962, 8, (2), pp. 179–187.
17. 17)
  - 33. German traffic sign dataset webpage. Available at http://benchmark.ini.rub.de/index.php?section=gtsrb&subsection=results.
18. 18)
  - 25. Song, Z.-H., Zhao, B., Zhu, Z.-X., et al: ‘Research on traffic number recognition based on neural network and invariant moments’. Proc. of the Sixth Int. Conf. on Machine Learning and Cybernetics, Hong Kong, 2007, pp. 19–22.
19. 19)
  - 19. Chang, C.-C., Lin, C.-J.: ‘LIBSVM: a library for support vector machines’, ACM Trans. Intell. Syst. Technol., 2011, 2, (3), pp. 1–27.
20. 20)
  - 15. Han, Y., Virupakshappa, K., Pinto, E.V.S., et al: ‘Hardware/Software co-design of a traffic sign recognition system using Zynq FPGAs’, Electronics, 2015, 2015, (4), pp. 1062–1089.
21. 21)
  - 4. Paulo, C.F., Correia, P.L.: ‘Automatic detection and classification of traffic signs’. 8th Int. Workshop on Image Analysis for Multimedia Interactive Services, Santorini, Greece, Paper No. 11, 2007.
22. 22)
  - 16. Kumaraswamy, R., Prabhu, L.V., Suchithra, K., et al: ‘SVM based classification of traffic signs for realtime embedded platform’, Adv. Comput. Commun., 2011, 193, pp. 339–348.
23. 23)
  - 18. Su, C.-L., Chen, K.-P., Chen, B.-H., et al: ‘Real-time implementation and design of an embedded system for identifying speed limit sign’. IEEE Int. Conf. on Consumer Electronics, Taipei, Taiwan, 2014, pp. 71–72.
24. 24)
  - 14. Hoang, A.-T., Yamamoto, M., Koide, T.: ‘High accuracy and simple real-time circle detection on low-cost FPGA for traffic-sign recognition on advanced driver assistance system’. The 19th Workshop on Synthesis and System Integration of Mixed Information Technologies, Yilan, Taiwan, 2015, pp. 397–402.
25. 25)
  - 29. Android NDK webpage. Available at http://developer.android.com/ndk/guides/index.html.
26. 26)
  - 8. Greenhalgh, J., Mirmehdi, M.: ‘Real-time detection and recognition of road traffic signs’, IEEE Trans. Intell. Transp. Syst., 2012, 13, (4), pp. 1498–1506.
27. 27)
  - 21. OpenCV Structural Analysis and Shape Descriptors Webpage. Available at http://docs.opencv.org/2.4/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html.
28. 28)
  - 5. Bui-Ninh, T., Ghita, O., Whelan, P.F., et al: ‘A robust algorithm for detection and classification of traffic signs in video data’. Int. Conf. on Control, Automation and Information Sciences, Ho Chi Minh City, Vietnam, 2012, pp. 108–113.
29. 29)
  - 31. Radxa Rock Pro webpage. Available at http://wiki.radxa.com/Rock.
30. 30)
  - 20. Tsai, C.-Y., Liu, T.-Y.: ‘Real-time automatic multilevel color video thresholding using a novel class-variance criterion’, Mach. Vis. Appl., 2015, 26, (2-3), pp. 233–249.
31. 31)
  - 23. Kiran, C.G., Prabhu, L.V., Rahiman, V.A., et al: ‘Support vector machine learning based traffic sign detection and shape classification using distance to borders and distance from center features’. IEEE Region 10 Conf., Hyderabad, India, 2008, pp. 1–6.
32. 32)
  - 12. Hoang, A.-T., Omori, M., Yamamoto, M., et al: ‘Compact pipeline hardware architecture for pattern matching on real-time traffic signs detection’. The 18th Workshop on Synthesis and System Integration of Mixed Information Technologies, Sapporo, Japan, 2013, pp. 100–105.
33. 33)
  - 30. OpenCV4Android SDK webpage. Available at http://docs.opencv.org/2.4/doc/tutorials/introduction/android_binary_package/O4A_SDK.html.
34. 34)
  - 10. Zaklouta, F., Stanciulescu, B.: ‘Real-time traffic-sign recognition using tree classifiers’, IEEE Trans. Intell. Transp. Syst., 2012, 13, (4), pp. 1507–1514.

Real-time embedded implementation of robust speed-limit sign recognition using a novel centroid-to-contour description method

References

Related content