A Fast and Precise HOG-Adaboost Based Visual Support System Capable to Recognize Pedestrian and Estimate Their Distance

  • Kishino Takahisa
  • Zhe Sun
  • Ruggero Micheletto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8158)

Abstract

In this paper,we present a visual support system the visually impaired. Our detection algorithm is based on the well known Histograms of Oriented Gradients (HOG) method, due to its high detection rate and versatility [5]. However, the accuracy of object recognition rate is reduced because of high false detection rate. In order to solve that, multiple parts model and triple phase detection have been implemented. These additional filtering stages were conducted by separate action on different area of the sample, considering deformations and translations. We demonstrated that this approach has raised the accuracy and speed of calculation. Through an evaluation experiment based on a large dataset, we found that false detection has been improved by 18.9% in respect to standard HOG detectors. Experimental tests have also shown the system ability to estimate the distance of the pedestrian by the use of a simple perspective model. The system has been tested on several photographic datasets and have shown excellent performances also in ambiguous cases.

Keywords

Pedestrian detection HOG methods distance evaluation single-camera Adaboost 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brasnett, P., Mihaylova, L., Bull, D., Canagarajah, N.: Sequential monte carlo tracking by fusing multiple cues in video sequences. Image vision Computing 25(8), 1217–1227 (2007)CrossRefGoogle Scholar
  2. 2.
    Cuevas, E., Zaldiver, D., Rojas, R.: Kalman filter for vision tracking. Fachbereich Mathematik und Informatic. Technical Report B, Freie Universitat Berlin (2005)Google Scholar
  3. 3.
    Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. Pattern Analysis and Machine Intelligence 2 (2006)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  5. 5.
    Suard, F., Rakotomamonjy, A., Bensrhair, A., Broggi, A.: Pedestrian detection using infrared images and histograms of oriented gradients. In: Proc. IEEE Conf. Intell. Vehicles, pp. 206–212 (2006)Google Scholar
  6. 6.
    Felzenszwalb, P., Girschick, R., McAllester, D.: Cascade object detection with deformable part models. In: CVPR, pp. 1–8 (2010)Google Scholar
  7. 7.
    Han, F., Shan, Y., Cekander, R., Sawhney, H.S., Kumar, R.: A two-stage approach to people and vehicle detection with hog-based svm. In: Performance Metrics for Intelligent Systems Workshop in conjunction with the IEEE Safety, Security, and Rescue Robotics Conference, pp. 134–136 (2006)Google Scholar
  8. 8.
    Helal, A., Moore, S., Ramachandran, B.: Drishti: An integrated navigation system for the visually impaired and disabled. In: Fifth International Symposium on Wearable Computers (ISWC 2001), pp. 149–156 (2001)Google Scholar
  9. 9.
    Juan, L., Gwun, O.: A comparison of sift, pca-sift and surf. International Journal of Image Processing 3, 143–152 (2009)Google Scholar
  10. 10.
    Montabone, S., Soto, A.: Human detection using a mobile platform and novel features derived from a visual saliency mechanism. Image and Vision Computing 28(3), 391–402 (2010)CrossRefGoogle Scholar
  11. 11.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. Pattern Analysis and Machine Intelligence, 1627–1645 (2010)Google Scholar
  12. 12.
    Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: Fast human detection using a cascade of histograms of oriented gradients. Mitsubishi Electric Research Laboratories, pp. 1491–1498 (2006)Google Scholar
  13. 13.
    Yan, X., Luo, Y.: Recognizing human actions using a new descriptor based on spatial-temporal interest points and weighted-output classifier. Neurocomputing 87, 51–61 (2012)CrossRefGoogle Scholar
  14. 14.
    Zhang, T., Liu, S., Xu, C., Lu, H.: Boosted multi-class semi-supervised learning for human action recognition. Pattern Recognition 44(10-11, SI), 2334–2342 (2011)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Kishino Takahisa
    • 1
  • Zhe Sun
    • 1
  • Ruggero Micheletto
    • 1
  1. 1.Graduate School of NanobioscienceYokohama City UniversityYokohamaJapan

Personalised recommendations