Advertisement

Detection of Pedestrians Based on the Fusion of Human Characteristics and Kernel Density Estimation

  • Shi Cheng
  • Muyan Zhou
  • Chunhong Lu
  • Yuanjin LiEmail author
  • Zelin Wang
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 986)

Abstract

The kernel density estimate does not need to have the characteristic distribution hypothesis to the background, it also does not require the estimation parameter, and it can deal with the moving target detection under the complex background, but the kernel function bandwidth choice uniformly puzzles the algorithm application. To solve this problem, this paper proposes a fusion method of human body characteristics and kernel density estimation for pedestrian detection. Firstly, the kernel function bandwidth is chosen by the prior information of moving target, then the foreground (moving target) is extracted based on kernel density estimation, finally, using human features to detect video pedestrians. The experimental results show that the calculation of kernel density estimation is reduced by comparing introduction of prior information with traditional methods, and the pedestrian and no pedestrian can be detected accurately by the interference of light variation and noise.

Keywords

Moving target Priori information Kernel density estimation Pedestrians 

Notes

Acknowledgment

This project is supported by Anhui University Natural Science Research Project (No. KJ2018A0431), Jiangsu Modern Educational Technology Research Project (No. 2017-R-54131), Nantong Science and Technology Project (No. MS12016036), Research on Teaching Reform at Nantong University (No. 2018043).

References

  1. 1.
    Shao, L., Liu, Y., Zhang, J.: Human action segmentation and recognition via motion and shape analysis. Pattern Recogn. Lett. 33(4), 438–445 (2012)CrossRefGoogle Scholar
  2. 2.
    Matsubara, T., Hyon, S.-H., Morimoto, J.: Real-time stylistic prediction for whole-body human motions. Neural Netw. 25, 191–199 (2012)CrossRefGoogle Scholar
  3. 3.
    Chen, D., Ren, S., Wei, Y., Cao, X., Sun, J.: Joint cascade face detection and alignment. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 109–122. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10599-4_8CrossRefGoogle Scholar
  4. 4.
    Elgammal, A., Harwood, D., Davis, L.: Non-parametric model for background subtraction. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 751–767. Springer, Heidelberg (2000).  https://doi.org/10.1007/3-540-45053-X_48CrossRefGoogle Scholar
  5. 5.
    Wang, L., Weiming, H., Tan, T.: Identification based on gait. J. Comput. Sci. 26(3), 353–360 (2003)Google Scholar
  6. 6.
    Wang, L., Hu, W., Tan, T.: Recent developments in human motion analysis. Pattern Recogn. 36(3), 585–601 (2003)CrossRefGoogle Scholar
  7. 7.
    Zhang, L., Yu, H.: Tracking method of human body occlusion under dual camera. Chin. J. Graph. Graph. 16(4), 606–612 (2011)Google Scholar
  8. 8.
    Sun, Y., Weng, P.: Study on pedestrian recognition and tracking based on particle swarm optimization algorithm. Comput. Eng. Des. 32(3), 988–994 (2011)Google Scholar
  9. 9.
    Sun, J., Chen, Y., Ji, Z.: Kernel density estimation background modeling method based on key frames. Opt. Technol. 34(5), 699–701 (2008)Google Scholar
  10. 10.
    Yu, J., Xu, D., Liao, Q.: Research progress of image fog technology. Chin. J. Graph. 16(9), 1561–1576 (2011)Google Scholar
  11. 11.
    Jin, T., Zhou, F., Bai, X.: Detection of motion target for space-based video based on kernel density estimation. Infrared Laser Eng. 40(1), 153–157 (2011)Google Scholar
  12. 12.
    Liu, Y.: Research on algorithm of moving target detection and tracking based on super pixel. Master’s degree thesis of China University of Science and Technology, Hefei (2013)Google Scholar
  13. 13.
    Rui, L., Lei, Z.: Design of syntactic parsing unit for structural pattern recognition system based on relational algebra. J. Dalian Jiaotong Univ. 33(3), 59–63 (2012)Google Scholar
  14. 14.
    Chen, F., Shui, A., Li, L.: Small sample pattern recognition method for pipeline plugging in storage and transportation process. Comput. Appl. Res. 31(7), 2031–2034 (2014)Google Scholar
  15. 15.
    Peng, D.: Research on brain activity of paired association learning in visual haptic cross pattern. Doctoral dissertations of East China Normal University, Shanghai (2015)Google Scholar
  16. 16.
    Cheng, X.: Research on pattern recognition framework APRF based on multi agent. Doctoral dissertations of Nanjing University of Science and Technology, Nanjing (2006)Google Scholar
  17. 17.
    Di, J., Yin, J.: Application of Wavelet Analysis. Science Press, Beijing (2017)Google Scholar
  18. 18.
    Haken, H. (Yang Jia-ben translated): Work with Computer and Cognitive - Top-Down Method of Neural Network. Tsinghua University Press, Beijing (1994)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Shi Cheng
    • 1
  • Muyan Zhou
    • 1
  • Chunhong Lu
    • 1
  • Yuanjin Li
    • 2
    Email author
  • Zelin Wang
    • 1
  1. 1.School of Computer Science and TechnologyNantong UniversityNantongChina
  2. 2.School of Computer and Information EngineeringChuzhou UniversityChuzhouChina

Personalised recommendations