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

access icon free Night-time pedestrian classification with histograms of oriented gradients-local binary patterns vectors

  • Author(s): Patrick Hurney 1 ; Peter Waldron 2 ; Fearghal Morgan 3 ; Edward Jones 1 ; Martin Glavin 1
    • View affiliations
    • Affiliations: 1: Connaught Automotive Research Group, School of Electrical and Electronic Engineering, College of Engineering and Informatics, National University of Ireland Galway, Galway City, Ireland;
      2: Intel Shannon, Dromore House, Shannon, Clare, Ireland;
      3: School of Electrical and Electronic Engineering, College of Engineering and Informatics, National University of Ireland Galway, Galway City, Ireland
  • Source: Volume 9, Issue 1, February 2015, p. 75 – 85
    DOI:  10.1049/iet-its.2013.0163 , Print ISSN 1751-956X, Online ISSN 1751-9578
© The Institution of Engineering and Technology
Received 02/10/2013, Accepted 20/02/2014, Revised 03/02/2014, Published 14/04/2014

The use of night vision systems in vehicles is becoming increasingly common, not just in luxury cars but also in the more cost sensitive sectors. Numerous approaches using infrared sensors have been proposed in the literature to detect and classify pedestrians in low visibility situations. However, the performance of these systems is limited by the capability of the classifier. This paper presents a novel method of classifying pedestrians in far-infrared automotive imagery. Regions of interest are segmented from the infrared frame using seeded region growing. A novel method of filtering the region growing results based on the location and size of the bounding box within the frame is described. This results in a smaller number of regions of interest for classification, leading to a reduced false positive rate. Histograms of oriented gradient features and local binary pattern features are extracted from the regions of interest and concatenated to form a feature for classification. Pedestrians are tracked with a Kalman filter to increase detection rates and system robustness. Detection rates of 98%, and false positive rates of 1% have been achieved on a database of 2000 images and streams of video; this is a 3% improvement on previously reported detection rates.

Inspec keywords: feature extraction; filtering theory; image segmentation; pedestrians; support vector machines; automobiles; infrared detectors; traffic engineering computing; image classification

Other keywords: low-cost infrared sensors; detection rates; seeded region growing; histogram of oriented gradient feature extraction; reduced false positive rate; support vector machine classifier; night vision systems; region of interest; bounding box; histogram of oriented gradient-local binary pattern vectors; RoF; captured infrared frame; high end luxury cars; far infrared automotive image streams; ROI; local binary pattern feature extraction; night-time pedestrian classification; filtering method; Kalman filter

Subjects: Image recognition; Computer vision and image processing techniques; Knowledge engineering techniques; Filtering methods in signal processing; Traffic engineering computing

References

    1. 1)
      • 25. Cheng, W.C., Jhan, D.M.: ‘A cascade classifier using Adaboost algorithm and support vector machine for pedestrian detection’. 2011 IEEE Int. Conf. Systems, Man, and Cybernetics (SMC), October 2011, pp. 1430–1435.
    2. 2)
      • 17. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, June 2004, vol. 1, pp. 886–893.
    3. 3)
      • 34. Bertozzi, M., Broggi, A., Grisleri, P., Tibaldi, A., Rose, M.D.: ‘A tool for vision based pedestrian detection performance evaluation’. 2004 IEEE Intelligent Vehicles Symp., June 2004, pp. 784–789.
    4. 4)
    5. 5)
      • 6. Kaparias, I., Bell, M.G.H.: ‘Testing a reliable in-vehicle navigation algorithm in the field’, IET Intell. Transp. Syst., 2012, 36, pp. 314–324.
    6. 6)
    7. 7)
      • 1. European New Car Assessment Program (Euro NCAP): http://www.euroncap.com/, accessed January 2014.
    8. 8)
    9. 9)
      • 23. Wang, X., Han, X., Yan, S.: ‘An HOG-LBP human detector with partial occlusion handling’. IEEE 12th Int. Conf. Computer Vision, October 2009, pp. 32–39.
    10. 10)
      • 14. Sivaraman, S., Trivedi, M.: ‘Active learning for on-road vehicle detection: a comparative study’, Mach. Vis. Appl., 2011, 6, pp. 1–13.
    11. 11)
      • 7. Unger, C., Wahl, E., Ilic, S.: ‘Parking assistance using dense motion-stereo’, Mach. Vis. Appl., 2011, 6, pp. 1–21.
    12. 12)
      • 9. Hanqvist, M.: ‘An object detection system’, Autoliv Department AB, May 2008, WO 2008/057042.
    13. 13)
      • 24. Guo, L., Li, L., Zhao, Y., Zhang, M.: ‘Study on pedestrian detection and tracking with monocular vision’. 2010 Second Int. Conf. Computer Technology and Development (ICCTD), November 2010, pp. 466–470.
    14. 14)
      • 30. Molina, J., Escudero-Violo, M., Signoriello, A., et al: ‘Real-time user independent hand gesture recognition from time-of-flight camera video using static and dynamic models’, Mach. Vis. Appl., 2011, 6, pp. 1–18.
    15. 15)
      • 10. Fang, Y., Yamada, K., Ninomiya, Y., Horn, B., Masaki, I.: ‘Comparison between infrared-image-based and visible-image-based approaches for pedestrian detection’. IEEE Intelligent Vehicles Symp., June 2003, pp. 505–510.
    16. 16)
    17. 17)
      • 18. Chang, F., Yang, X., Wu, W.P., Cho, Y.A., Chen, S.W.: ‘Night-time pedestrian detection using thermal imaging based on HOG feature’. Int. Conf. System Science and Engineering, June 2011, pp. 694–698.
    18. 18)
    19. 19)
      • 35. Bertozzi, M., Broggi, A., Ghidoni, S., Meinecke, M.M.: ‘A night vision module for the detection of distant pedestrians’. 2007 IEEE Intelligent Vehicles Symp., June 2007, pp. 25–30.
    20. 20)
      • 37. Bertozzi, M., Broggi, A., Del Rose, M., Felisa, M., Rakotomamonjy, A., Suard, F.: ‘A pedestrian detector using histograms of oriented gradients and a support vector machine classifier’. IEEE Conf. Intell. Trans. Syst., October 2007, pp. 143–148.
    21. 21)
      • 38. Sun, H., Wang, C., Wang, B.: ‘Night vision pedestrian detection using a forward-looking infrared camera’. 2011 Int. Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping (M2RSM), 2011, pp. 1–4.
    22. 22)
    23. 23)
      • 16. Shashua, A., Gdalyahu, Y., Hayun, G.: ‘Pedestrian detection for driving assistance systems: single-frame classification and system level performance’. IEEE Intelligent Vehicles Symp., June 2004, pp. 1–6.
    24. 24)
      • 15. Gavrila, D.M., Giebel, J.: ‘Shape-based pedestrian detection and tracking’, IEEE Intell. Veh. Symp., 2002, 1, pp. 8–14.
    25. 25)
      • 13. O'Malley, R., Glavin, M., Jones, E.: ‘An efficient region of interest generation technique for far-infrared pedestrian detection’. ICCE Int. Conf. Consumer Electronics, January 2008, pp. 1–2.
    26. 26)
      • 3. European Road Safety Observatory: ‘Traffic Safety Basic Facts 2012 – pedestrians’, March 2012.
    27. 27)
      • 27. Tsimhoni, J.B.O., Minoda, T., Flanagan, M.J.: ‘Pedestrian detection with near and far infrared night vision enhancement’, IEEE Trans. Intell. Transp. Syst., 2004, 6, pp. 63–71.
    28. 28)
      • 31. Welch, G., Bishop, G.: ‘An introduction to the Kalman filter’, Tech. Rep. TR 95–041, University of North Carolina at Chapel Hill, Department of Computer Science, 2003.
    29. 29)
      • 36. Bertozzi, M., Broggi, A., Lasagni, A., Rose, M.D.: ‘Infrared stereo vision-based pedestrian detection’. 2005 IEEE Intelligent Vehicles Symp., June 2005, pp. 24–29.
    30. 30)
      • 22. Li, S.Z., Zhang, L., Liao, S., et al: ‘A near-infrared image based face recognition system’. IEEE Seventh Int. Conf. Automatic Face and Gesture Recognition (FGR), April 2006, pp. 455–460.
    31. 31)
      • 33. Ge, J., Luo, Y., Tei, G.: ‘Real-time pedestrian detection and tracking at nighttime for driver-assistance systems’. IEEE Intelligent Vehicles Symp., June 2004, pp. 1–6.
    32. 32)
      • 28. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’. Int. Journal of Comp. Vision, 2004, pp. 91–110.
    33. 33)
      • 19. Xia, D., Sun, H., Shen, Z.: ‘Real-time infrared pedestrian detection based on multi-block LBP’. 2010 Int. Conf. on Computer Application and System Modeling (ICCASM), October 2010, vol. 12, pp. 139–142.
    34. 34)
      • 39. Suard, F., Rakotomamonjy, A., Bensrhair, A., Broggi, A.: ‘Pedestrian detection using infrared images and histograms of oriented gradients’. IEEE Intelligent Vehicles Symp., June 2006, pp. 206–212.
    35. 35)
      • 2. Hobbs, A.: ‘Euro NCAP/MORI survey on consumer buying interests (speech and presentation)’. Proc. Euro NCAP Conf.: Creating a Market for Safety 10 years of Euro NCAP, Brussels, Belgium, November 2005.
    36. 36)
    37. 37)
    38. 38)
      • 32. Teoh, S., Brunl, T.: ‘Symmetry-based monocular vehicle detection system’, Mach. Vis. Appl., 2011, 6, pp. 1–12.
    39. 39)
      • 29. Zhiguo, N., Xuehong, Q.: ‘Facial expression recognition based on weighted principal component analysis and support vector machines’. 2010 Third Int. Conf. Advanced Computer Theory and Engineering (ICACTE), 2010, vol. 3, pp. 174–178.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2013.0163
Loading

Related content

content/journals/10.1049/iet-its.2013.0163
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address