Advertisement

Research on Evaluation Model of Danger Degree in Driving

  • Keyou Guo
  • Yiwei Wang
  • Xiaoli Guo
  • Qichao Bao
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 503)

Abstract

The existing safe driving model all evaluated the potential dangers in driving based on single-factor analysis results. This study proposed a multifactor driving danger evaluation model including three factors—lane, vehicle distance, and vehicle type. The abstract information of lane, vehicle type, and vehicle distance was first quantified as specific values; then, we conducted crossover analysis on the quantified parameter and established the linear model; finally, through multiple regression, the logical relationships between these three factors and danger coefficient were acquired. Meanwhile, the model parameters were analyzed based on the theory in statistics. Results demonstrate that the proposed danger evaluation model can reasonably describe the effects of these three factors on the safety in driving.

Keywords

Safe driving Evaluation model Multiple regression Lane detection Vehicle distance detection Vehicle type recognition 

References

  1. 1.
    Xu M, Zhang K, Jiang Z (2013) Algorithm design and implementation for a real-time lane departure pre-warning system. J Traffic Transp Eng 16(3):149–158Google Scholar
  2. 2.
    Chen B (2013) Lane recognition and departure warning based on hyperbolic model. J Comput Appl 3:2562–2565CrossRefGoogle Scholar
  3. 3.
    Peng J, Wang J, Wang N (2011) Intelligent vehicle collision warning algorithm based on machine vision. J Highw Transp Res Dev 28(S1):124–128Google Scholar
  4. 4.
    Liu Z, Wen H (2007) Monocular vision-based vehicle collision warning system. Comput Appl 27(8):2056–2058Google Scholar
  5. 5.
    Zhong Y, Yao J (2001) A formula of the critical safety distance between two moving vehicles. J Hunan Univ (Nat Sci Ed) 28(6):54–58Google Scholar
  6. 6.
    Feng Z, Yuan H, Liu J, Zhang WH, Liu H (2012) Influence of driver personal characteristics on vehicle velocity. J Traffic Transp Eng 12(6):89–96Google Scholar
  7. 7.
    Guo Y, Ma Y, Fu R, Meng N, Yuan W (2012) Influence of driving experience on gazing behavior characteristic for car driver. J Traffic Transp Eng 12(5):89–96Google Scholar
  8. 8.
    Jelsovka D, Hudec R, Breznan M (2011) Face recognition on FERET face database using LDA and CCA methods. Int Conf Telecommun Signal Process 2011:570–574Google Scholar
  9. 9.
    Yoo H, Yang U, Sohn K (2013) Gradient-enhancing conversion for illumination-robust lane detection. IEEE Trans Intell Transp Syst 14(3):1083–1094CrossRefGoogle Scholar
  10. 10.
    Guo K, Wang Y, Guo X Lane classification algorithm combined LDA and LSD. Comput Eng Appl, 1–8Google Scholar
  11. 11.
    Du X, He Y, Chen L, Gao S (2016) Pose estimation of large non-cooperative spacecraft based on extended PnP model. 2016 IEEE international conference on robotics and biomimetics (ROBIO), Qingdao, 2016, pp 413–418Google Scholar
  12. 12.
    Chi D, Wang Y, Ning L, Yi J (2015) Experimental research of camera calibration based on ZHANG’s method. J Chin Agric Mech 36(2):287–289, 337Google Scholar
  13. 13.
    Ma T, Yao R, Shao Y, Zhou R (2009) A SVD-based method to assess the uniqueness and accuracy of SPECT geometrical calibration. IEEE Trans Med Imaging 28(12):1929–1939CrossRefGoogle Scholar
  14. 14.
    Israni S, Jain S (2016) Edge detection of license plate using Sobel operator. 2016 International conference on electrical, electronics, and optimization techniques (ICEEOT), Chennai, pp 3561–3563Google Scholar
  15. 15.
    Fengmei Sun, Weining Wang (2006) Pose determination from a single image of a single parallelogram. ACTA AUTOMATICA SINICA 32(5):746–752MathSciNetGoogle Scholar
  16. 16.
    Sun Q, Lu X, Chen L, Hu H (2014) An improved vehicle logo recognition method for road surveillance images. Seventh Int Symp Comput Intell Des Hangzhou 2014:373–376Google Scholar
  17. 17.
    Guzman S, Gomez A, Diez G, Fernandez DS (2015) Car detection methodology in outdoor environment based on histogram of oriented gradient (HOG) and support vector machine (SVM). 6th Latin-American conference on networked and electronic media (LACNEM 2015), Medellin, 2015, pp 1–4Google Scholar
  18. 18.
    Lee SH, Bang M, Jung KH, Yi K (2015) An efficient selection of HOG feature for SVM classification of vehicle. Int Symp Consum Electron (ISCE) Madrid 2015:1–2Google Scholar
  19. 19.
    Xie G, Wang Z, Hei X, Takahashi S, Nakamura H (2016) Data-based axle temperature prediction of high speed train by multiple regression analysis. 2016 12th international conference on computational intelligence and security (CIS), Wuxi, 2016, pp 349–353Google Scholar
  20. 20.
    Kitamura T, Tsujiuchi N, Koizumi T (2006) Hand motion estimation by EMG signals using linear multiple regression models. 2006 international conference of the IEEE engineering in medicine and biology society, New York, NY, 2006, pp 1339–1342Google Scholar
  21. 21.
    Liu Z, Ott J, Shen Y (2010) P-value distribution in case-control association studies. 2010 IEEE international conference on bioinformatics and biomedicine workshops (BIBMW), Hong, Kong, 2010, pp 306–308Google Scholar
  22. 22.
    Rögnvaldsson T, Norrman H, Byttner S, Järpe E (2014) Estimating p-values for deviation detection. 2014 IEEE eighth international conference on self-adaptive and self-organizing systems, London, 2014, pp 100–109Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Material Science and Mechanical EngineeringBeijing Technology and Business UniversityBeijingChina

Personalised recommendations