Multimedia Tools and Applications

, Volume 78, Issue 21, pp 29747–29763 | Cite as

Motion estimation of indoor robot based on image sequences and improved particle filter

  • Xiaoming Dong
  • Liefu Ai
  • Rong JiangEmail author


Robot motion estimation is fundamental in most robot applications such as robot navigation, which is an indispensable part of future internet of things. Indoor robot motion estimation is difficult to be resolved because GPS (Global Positioning System) is unavailable. Vision sensors can provide larger amount of image sequences information compared with other traditional sensors, but it is subject to the changes of light. In order to improve the robustness of indoor robot motion estimation, an enhanced particle filter framework is constructed: firstly, motion estimation was implemented based on the distinguished indoor feature points; secondly, particle filter method was utilized and the least square curve fitting was inserted into the particle resampling process to solve the problem of particle depletion. The various experiments based on real robots show that the proposed method can reduce the estimation errors greatly and provide an effective resolution for the indoor robot localization and motion estimation.


Internet of things Visual odometry Indoor robot Localization Motion estimation 



The paper was supported by National Natural Science Foundation of China (Nos. 61763048,61263022, 61303234), National Social Science Foundation of China (No. 12XTQ012), Science and Technology Foundation of Yunnan Province (Nos. 2017FB095, 201801PF00021), the 18th Yunnan Young and Middle-aged Academic and Technical Leaders Reserve Personnel Training Program (No.2015HB038). It is also supported by the Foundation of University Research and Innovation Platform Team for Intelligent Perception and Computing of Anhui Province, key research project of natural science of Anhui Provincial Education Department (KJ2017A354). Anhui Provincial Natural Science Foundation of China (1608085MF144). The authors would like to thank the anonymous reviewers and the editors for their suggestions.

Author’s contributions

Rong Jiang, Xiaoming Dong designed the experiments and wrote the paper; Rong Jiang, Xiaoming Dong performed the experiments; Liefu Ai analyzed the data; All authors have read and approved the final manuscript.

Compliance with ethical standards

Competing interests

The authors declare that they have no competing interests.


  1. 1.
    Alon J, Sclaroff S (2000) Recursive estimation of motion and planar structure. In: IEEE computer vision and pattern recognition, pages II:550–556Google Scholar
  2. 2.
    Ascani A, Frontoni E, Mancini A 2008 Feature group matching for appearance-based localization. In: IROSGoogle Scholar
  3. 3.
    Azarbayejani A, Pentland AP (1995) Recursive estimation of motion, structure, and focal length, IEEE transactions on pattern analysis and machine intelligence. 17(6):562–575CrossRefGoogle Scholar
  4. 4.
    Bortz JE (2007) A new mathematical formulation for strapdown inertial navigation. IEEE Trans Aerosp Electron Syst AES-7(1):61–66MathSciNetCrossRefGoogle Scholar
  5. 5.
    Bronzwaer S, Cars O, Buchholz U et al (2002) A European study on the relationship of antimicrobial use and antimicrobial resistance[J]. Emerg Infect Dis 8(3):278–282CrossRefGoogle Scholar
  6. 6.
    Campbell J, Sukthankar R, Nourbakhsh I (2004) Techniques for evaluating optical flow in extreme terrain. Proceedings of IROSGoogle Scholar
  7. 7.
    Carlevaris-Bianco N, Kaess M, Eustice RM (2017) Generic node removal for factor-graph SLAM[J]. IEEE Trans Robot 30(6):1371–1385CrossRefGoogle Scholar
  8. 8.
    Cumani A, Guiducci A (2009) ,Comparison of feature detectors for rover navigation. MMCTEE pp.126-131. Google Scholar
  9. 9.
    Davison AJ, Reid ID, Molton ND et al (2007) MonoSLAM: real-time single camera SLAM[J]. IEEE Trans Pattern Anal Mach Intell 29(6):1052–1067CrossRefGoogle Scholar
  10. 10.
    Eckenhoff K, Paull L, Huang G (2016) Decoupled, consistent node removal and edge sparsification for graph-based SLAM[C]. IEEE international conference on intelligent robots and systems pp 3275–3282Google Scholar
  11. 11.
    Helmick DM, Chang Y, Roumeliotis SI, Clouse D, Matthies L (2004) Path following using visual odometry for a mars rover in high-slip environments. In: Proc. 2004 IEEE Aerospace Conference, Big Sky, MT,Mar. 6–13, 2004Google Scholar
  12. 12.
    Indelman V (2017) No correlations involved: decision making under uncertainty in a conservative sparse information space[J]. IEEE Robot Autom Lett 1(1):407–414CrossRefGoogle Scholar
  13. 13.
    Kandepu R, Foss B, Imsland L (2008) Applying the unscented Kalman filter for nonlinear state estimation[J]. J Process Control 18(7):753–768CrossRefGoogle Scholar
  14. 14.
    Lowe DG (2004) Distinctive image features from scale invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  15. 15.
    Magnabosco M, Breckon TP (2013) Cross-spectral visual simultaneous localization and mapping (SLAM) with sensor handover. Robot Auton Syst 63(2):195–208CrossRefGoogle Scholar
  16. 16.
    Montemerlo M, Thrun S, Koller D et al (2002) FastSLAM: a factored solution to the simultaneous localization and mapping problem[C], AAAI pp 593–598Google Scholar
  17. 17.
    Ning M, Zhang S, Wang S (2018) A non-cooperative satellite feature point selection method for vision-based navigation system. Sensors 18:854CrossRefGoogle Scholar
  18. 18.
    Olson C F, Matthies L H, Schoppers M, et al. (2003). Rover Navigation using Stereo Ego-motion[J]. Rob Auton Syst 43(4):215–229.CrossRefGoogle Scholar
  19. 19.
    Potkonjak M, Feng J, Girod L (2006) Location discovery using data drive statistical error modeling[J]. IEEE FOCOM 26(8):43–47Google Scholar
  20. 20.
    Sajeeb R, Manohar CS, Roy D (2009) Rao-Blackwellization with substructuring for state and parameter estimations of a class of nonlinear dynamical systems. IJEUU 1:1–2Google Scholar
  21. 21.
    Sirtkaya S, Seymen B, Alatan AA (2013) Loosely coupled Kalman filtering for fusion of visual odometry and inertial navigation. In: Proceedings of the 2013 16th international conference on information fusion (FUSION), Istanbul, Turkey, 9–12 July 2013, pp 219–226Google Scholar
  22. 22.
    Ssu K-F, Ou C-H, Jiau HC (2005) Localization with mobile anchor points in wireless sensor networks[J]. IEEE Trans Veh Technol 54(3):1187–1197CrossRefGoogle Scholar
  23. 23.
    Torr PHS, Fitzgibbon A, Zisserman A (1999) The problem of degeneracy in structure and motion recovery from uncalibrated image sequences. Int J Comput Vis 32(1):27–45CrossRefGoogle Scholar
  24. 24.
    Wang H, Yuan K, Zou W, Zhou Q (2005) Visual odometry based on locally planar ground assumption, IEEE International Conference on Information Acquisition(ICIA2005)Google Scholar
  25. 25.
    Wang C, Wang T, Liang J, Chen Y, Wu Y (2012) Monocular vision and IMU based navigation for a small unmanned helicopter. In: Proceedings of the 2012 7th IEEE conference on Industrial Electronics and Applications (ICIEA), Singapore, 18–20 July 2012, pp 1694–1699Google Scholar
  26. 26.
    Wu J, Li J, Chen W (2017) Practical adaptive fuzzy tracking control for a class of perturbed nonlinear systems with backlash nonlinearity. Inf Sci 420:517–531CrossRefGoogle Scholar
  27. 27.
    Wu J, Wu Z-G, Li J, Wang G, Zhao H, Chen W (2018) Practical adaptive fuzzy control of nonlinear pure-feedback systems with quantized nonlinearity input. IEEE Trans Syst Man Cybern Syst Hum. CrossRefGoogle Scholar
  28. 28.
    Xu D, Han L, Tan M, Li YF (2009) Ceiling-based Visual Positioning for an Indoor Mobile Robot with Monocular Vision. IEEE Trans Ind Electron 56(5):1617–1628CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.The University Key Laboratory of Intelligent Perception and Computing of Anhui ProvinceAnqing Normal UniversityAnqingChina
  2. 2.School of InformationYunnan University of Finance and EconomicsKunmingChina

Personalised recommendations