Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free D-patches: effective traffic sign detection with occlusion handling

In advanced driver assistance systems, accurate detection of traffic signs plays an important role in extracting information about the road ahead. However, traffic signs are persistently occluded by vehicles, trees, and other structures on road. Performance of a detector decreases drastically when occlusions are encountered especially when it is trained using full object templates. Therefore, we propose a new method called discriminative patches (d-patches), which is a traffic sign detection (TSD) framework with occlusion handling capability. D-patches are those regions of an object that possess the most discriminative features than their surroundings. They are mined during training and are used for classification instead of the full object templates. Furthermore, we observe that the distribution of redundant-detections around a true-positive is different from that around a false-positive. Based on this observation, we propose a novel hypothesis generation scheme that uses a voting and penalisation mechanism to accurately select a true-positive candidate. We also introduce a new Korean TSD (KTSD) dataset with several evaluation settings to facilitate detector's evaluation under different conditions. The proposed method achieves 100% detection accuracy on German TSD benchmark and achieves 4.0% better detection accuracy, when compared with other well-known methods (under partially occluded settings), on KTSD dataset.

References

    1. 1)
      • 17. Boumediene, M., Lauffenburger, J., Daniel, J., et al: ‘Multi-ROI association and tracking with belief functions: application to traffic sign recognition’, IEEE TITS, 2014, 15, (6), pp. 24702479.
    2. 2)
      • 13. Ellahyani, A., Ansari, M., Jaafari, I., et al: ‘Traffic sign detection and recognition based on random forests’, ASC, 2016, 46, pp. 805815.
    3. 3)
      • 19. Wang, X., Han, T., Yan, S.: ‘An HOG-LBP human detector with partial occlusion handling’. IEEE ICCV, 2009, pp. 3239.
    4. 4)
      • 3. Greenhalgh, J., Mirmehdi, M.: ‘Real-time detection and recognition of road traffic signs’, IEEE TITS, 2012, 13, (4), pp. 14981506.
    5. 5)
      • 26. Andrea, V., Zisserman, A.: ‘Efficient additive kernels via explicit feature maps’, IEEE TPAMI, 2012, 34, (3), pp. 480492.
    6. 6)
      • 18. Felzenszwalb, P., Girshick, R., McAllester, D., et al: ‘Object detection with discriminatively trained part-based models’, IEEE TPAMI, 2010, 32, (9), pp. 16271645.
    7. 7)
      • 10. Aghdam, H., Heravi, E., Puig, D., et al: ‘A practical approach for detection and classification of traffic signs using convolutional neural networks’, RAS, 2016, 84, pp. 97112.
    8. 8)
      • 12. Eickeler, S., Valdenegro, M., Werner, T., et al: ‘Future computer vision algorithms for traffic sign recognition systems’. Springer AMAA, 2015, pp. 6977.
    9. 9)
      • 7. Dollár, P., Appel, R., Belongie, S., et al: ‘Fast feature pyramids for object detection’, IEEE TPAMI, 2014, 36, (8), pp. 15321545.
    10. 10)
      • 11. Berkaya, S., Gunduz, H., Ozsen, O., et al: ‘On circular traffic sign detection and recognition’, ESA, 2016, 48, pp. 6775.
    11. 11)
      • 16. Soilán, M., Riveiro, B., Martinez-Sánchez, J., et al: ‘Traffic sign detection in MLS acquired point clouds for geometric and image-based semantic inventory’, ISPRS-JPRS, 2016, 114, pp. 92101.
    12. 12)
      • 9. Zhu, Y., Zhang, C., Zhou, D., et al: ‘Traffic sign detection and recognition using fully convolutional network guided proposals’, Neurocomputing, 2016, 214, pp. 758766.
    13. 13)
      • 4. Liang, M., Yuan, M., Hu, X., et al: ‘Traffic sign detection by ROI extraction and histogram features-based recognition’. IJCNN, 2013, pp. 18.
    14. 14)
      • 29. Accessed from ‘ http://benchmark.ini.rub.de/?section=gtsdb=subsection=dataset’,2016.
    15. 15)
      • 8. Liu, C., Chang, F., Liu, C.: ‘Occlusion-robust traffic sign detection via cascaded colour cubic feature’, IET ITS, 2016, 10, (5), pp. 354360.
    16. 16)
      • 27. Larsson, F., Felsberg, M., et al: ‘Using Fourier descriptors and spatial models for traffic sign recognition’. Springer IA, 2011, pp. 238249.
    17. 17)
      • 20. Teng, Y., Hyunchul, S.: ‘Detecting partially occluded vehicles with geometric and likelihood reasoning’, IET CV, 2015, 9, (2), pp. 174183.
    18. 18)
      • 15. Yu, Y., Li, J., Wen, C., et al: ‘Bag-of-visual-phrases and hierarchical deep models for traffic sign detection and recognition in mobile laser scanning data’, ISPRS-JPRS, 2016, 113, pp. 106123.
    19. 19)
      • 24. Ojala, T., Pietikainen, M., Maenpaa, T.: ‘Multiresolution gray-scale and rotation invariant texture classification with local binary patterns’, IEEE TPAMI, 2002, 24, (7), pp. 971987.
    20. 20)
      • 23. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. Proc. IEEE CVPR, 2005.
    21. 21)
      • 5. Wang, G., Reney, G., Wu, Z., et al: ‘A robust, coarse-to-fine traffic sign detection method’. IJCNN, 2013, pp. 754758.
    22. 22)
      • 6. Hu, Q., Paisitkriangkrai, S., Shen, C., et al: ‘Fast detection of multiple objects in traffic scenes with a common detection framework’. IEEE TITS, 2015, pp. 113.
    23. 23)
      • 2. Liu, C., Chang, F., Chen, Z., et al: ‘Fast traffic sign recognition via high-contrast region extraction and extended sparse representation’, iIEEE TITS, 2016, 17, (1), pp. 7992.
    24. 24)
      • 21. Mogelmose, A., Liu, D., Trivedi, M.: ‘Detection of U.S. traffic signs’, IEEE TITS, 2015, 16, (6), pp. 31163125.
    25. 25)
      • 25. Rosipal, R., Kramer, N.: ‘Overview and recent advances in partial least squares in latent structures feature selection’ (Springer Verlag, 2006).
    26. 26)
      • 28. Chen, T., Lu, S.: ‘Accurate and efficient traffic sign detection using discriminative adaboost and support vector regression’, IEEE TVT, 2016, 65, (6), pp. 40064015.
    27. 27)
      • 14. Gudigar, A., Chokkadi, S., Raghavendra, U., et al: ‘Multiple thresholding and subspace based approach for detection and recognition of traffic sign’. Springer MTA, 2016, pp. 119.
    28. 28)
      • 1. Mogelmose, A., Trivedi, M., Moeslund, T.: ‘Vision-based traffic sign detection and analysis for intelligent driver assistance systems: perspectives and survey’, IEEE TITS, 2012, 13, (4), pp. 14841497.
    29. 29)
      • 22. Hyunchul, S., Teng, Y., Ismail, Y., et al: ‘Rendering high dynamic range images by using integrated global and local processing’, Opt. Eng., 2011, 50, (11), pp. 117002111700211.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0303
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0303
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address