Advertisement

An Improved Algorithm for Moving Object Tracking Based on EKF

  • Leichao HouEmail author
  • Junsuo Qu
  • Ruijun Zhang
  • Ting Wang
  • KaiMing Ting
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 891)

Abstract

Kalman filter estimates the desired signal from the amount of measurement related to the extracted signal, which is widely used in engineering due to its simple calculation and easy programming on a computer. However, the basic theory originally proposed by Rudolf E. Kalman is for linear systems only, whereas a realistic physical system is often nonlinear. Extended Kalman Filter (EKF) solves nonlinear filtering problems. In this paper, we focus on issues related with targeted object being occluded We combine EKF and Meanshift to track the moving object. Once the object position is predicted by EKF in the center of the object, then the Meanshift algorithm iterates over the initial value of EKF estimation to track the object. Experiments show that the method reduces the object search time and improves the accuracy of the object tracking.

Keywords

EKF Nonlinear system Meanshift Object tracking 

Notes

Acknowledgments

This research was supported in part by grants from the International Cooperation and Exchange Program of Shaanxi Province (2018 K W-026), Natural Science Foundation of Shaanxi Province (2018JM6120), Xi’an Science and Technology Plan Project (201805040YD18C G24(6)), Major Science and Technology Projects of XianYang City (2017k01-25-12), Graduate Innovation Fund of Xi’an University of Posts & Telecommunications (CXJJ2017012, CXJJ2017028, CXJJ 2017056).

References

  1. 1.
    Zhao, H.Y., Zhang, X.L., et al.: Image denoising algorithm based on multi-scale Meanshift. J. Jilin Univ. 44(5), 1417–1422 (2014).  https://doi.org/10.7964/jdxbgxb201405031MathSciNetCrossRefGoogle Scholar
  2. 2.
    He, L., Han, B.S., et al.: New definition of filled function applied to global optimization. Commun. Appl. Math. Comput. 30(1), 128–137 (2016).  https://doi.org/10.3969/j.issn.l006-6330.2016.01.011MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Ou, Y.N., You, J.H., et al.: Tracking multiple objects in occlusions. Appl. Res. Comput. 27(5), 1984–1986 (2010).  https://doi.org/10.3969/j.issn.1001-3695.2010.05.110CrossRefGoogle Scholar
  4. 4.
    Li, Z.L.: An visual object tracking algorithm based on improved camshift. Comput. Knowl. Technol. 12(9X), 150–152 (2016).  https://doi.org/10.14004/j.cnki.ckt.2016.3566CrossRefGoogle Scholar
  5. 5.
    Jin, G., Zhu, Z.Q.: Improvement and simulation of kalman filter localization algorithm for mobile robot. Ordnance Indus. Autom. (2018).  https://doi.org/10.7690/bgzdh.2018.04.017
  6. 6.
    Salhi, A., Moresly, Y., et al.: Modeling from an object and multi-object tracking system. In: Computer and Information Technology. IEEE (2017).  https://doi.org/10.1109/gscit.2016.20
  7. 7.
    Rhudy, M., Gu, Y., Napolitano, M.: An analytical approach for comparing linearization methods in EKF and UKF. Int. J. Adv. Rob. Syst. 10(10), 5870–5877 (2013).  https://doi.org/10.5772/56370CrossRefGoogle Scholar
  8. 8.
    Wang, B.Y., Fan, B.J.: Adoptive meanshift tracking algorithm based on the combined feature histogram of color and texture. J. Nanjing Univ. Posts Telecommun. 33(3), 18–25 (2013).  https://doi.org/10.14132/j.cnki.1673-5439.2013.03.017CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Leichao Hou
    • 2
    Email author
  • Junsuo Qu
    • 1
  • Ruijun Zhang
    • 2
  • Ting Wang
    • 2
  • KaiMing Ting
    • 3
  1. 1.School of AutomationXi’an University of Post and TelecommunicationsXi’anChina
  2. 2.School of Communication and EngineeringXi’an University of Post and TelecommunicationsXi’anChina
  3. 3.School of Science, Engineering and Information TechnologyFederation UniversityBallaratAustralia

Personalised recommendations