Abstract

In order to improve the function of driver-assistance system, this paper proposes a real-time detection method of zebra crossing based on the on-board monocular camera, it doesn’t only detect the zebra crossings we can see from the road, but also detect some zebra crossings obscured by other objects. Firstly, integral method based on horizontal projection is used to separate possible zebra crossings from lane. However, the integral of other road traffic signs may be similar to a zebra crossing, in order to overcome this problem, the number of identifier are calculated respectively for each effective projection region, it is obvious that the number of zebra crossing are more than others, experimental results show that our method proposed in this paper is effective.

Keywords

Traffic Signs zebra Crossings projection Integral detection 

Notes

Acknowledgements

This work was supported by Science Technique Department of Guizhou Province of China ([2014]2096).

References

  1. 1.
    Kheyrollahi A, Breckon TP (2012) Automatic real-time road marking recognition using a feature driven approach. Mach Vis Appl 23(1):123–133CrossRefGoogle Scholar
  2. 2.
    Sampathkumar J, Rajamani K (2013) Automatic detection of zebra crossing violation. In: Proceedings of the fourth international conference on signal and image processing 2012 (ICSIP 2012), India, pp 499–509Google Scholar
  3. 3.
    Ng HF (2004) Automatic thresholding for defect detection. Pattern Recogn Lett 27(14):1644–1649CrossRefGoogle Scholar
  4. 4.
    Zhou ZZ, Yu HY, Zhao ZF, Qiao XL. (2010) SS-based sketch recognition for graphics of traffic accident. In: Proceedings of seventh international conference on fuzzy systems and knowledge discovery Yantai, China, pp 2558–2562Google Scholar
  5. 5.
    Se S (2000) Zebra-crossing detection for the partially sighted. In: 2013 IEEE conference on computer vision and pattern recognition vol (2), pp 2211–2211Google Scholar
  6. 6.
    Wang C, Zhao C, Wang H (2014) Robust zebra-crossing detection for autonomous land vehicles and driving assistance systems. Appl Mech Mater 556–562:2732–2739Google Scholar
  7. 7.
    Li H, Feng MY, Wang X (2012) A zebra-crossing detection algorithm for intelligent vehicles. Appl Mech Mater 236–237:390–395Google Scholar
  8. 8.
    Ahmetovic D, Bernareggi C, Gerino A, Mascetti S (2014) Zebra recognizer: efficient and precise localization of pedestrian crossings. In: Proceedings of international conference on pattern recognition, pp 2566–2571Google Scholar
  9. 9.
    Chen ZS, Wu YF (2014) A segmentation method of traffic marking based on Average gray approximating the optimal threshold. In: Proceedings of conference on 2nd international conference on signal processing, image processing and pattern recognition Guilin, China, pp 3510–3513Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Guizhou University for NationalitiesGuiyangChina

Personalised recommendations