Advertisement

Tracking Registration Algorithm for Augmented Reality Based on Template Tracking

  • Peng-Xia CaoEmail author
  • Wen-Xin Li
  • Wei-Ping Ma
Research Article

Abstract

Tracking registration is a key issue in augmented reality applications, particularly where there are no artificial identifier placed manually. In this paper, an efficient markerless tracking registration algorithm which combines the detector and the tracker is presented for the augmented reality system. We capture the target images in real scenes as template images, use the random ferns classi- fier for target detection and solve the problem of reinitialization after tracking registration failures due to changes in ambient lighting or occlusion of targets. Once the target has been successfully detected, the pyramid Lucas-Kanade (LK) optical flow tracker is used to track the detected target in real time to solve the problem of slow speed. The least median of squares (LMedS) method is used to adaptively calculate the homography matrix, and then the three-dimensional pose is estimated and the virtual object is rendered and registered. Experimental results demonstrate that the algorithm is more accurate, faster and more robust.

Keywords

Tracking registration augmented reality markerless random ferns Lucas-Kanade (LK) optical flow 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgements

This work was supported by National Natural Science Foundation of China (No. 61125101).

References

  1. [1]
    J. P. Lima, R. Roberto, F. Simões, M. Almeida, L. Figueiredo, J. M. Teixeira, V. Teichrieb. Markerless tracking system for augmented reality in the automotive industry. Expert Systems with Applications, vol. 82, pp. 100–114, 2017. DOI:  https://doi.org/10.1016/j.eswa.2017.03.060.CrossRefGoogle Scholar
  2. [2]
    R. Frikha, R. Ejbali, M. Zaied. Camera pose estimation for augmented reality in a small indoor dynamic scene. Journal of Electronic Imaging, vol. 26, no. 5, Article number 053029, 2017. DOI:  https://doi.org/10.1117/1.JEI.26.5.053029.Google Scholar
  3. [3]
    F. P. Vista IV, D. J. Lee, K. T. Chong. Remote activation and confidence factor setting of ARToolKit with data association for tracking multiple markers. International Journal of Control and Automation, vol. 6, no. 6, pp. 243–252, 2013. DOI:  https://doi.org/10.14257/ijca.2013.6.6.23.CrossRefGoogle Scholar
  4. [4]
    M. Fiala. ARTag, An Improved Marker System Based on ARToolkit[J], NRC 47166/ERB-1111, National Research Council Canada, 2004. DOI:  https://doi.org/10.4224/5763247.Google Scholar
  5. [5]
    Y. Y. Du, Z. J. Miao, Y. G. Cen. Markless augmented reality registration algorithm based on ORB. In Proceedings of the 12th International Conference on Signal Processing, IEEE, Hangzhou, China, 1236–1240, 2015. DOI:  https://doi.org/10.1109/ICOSP.2014.7015197.Google Scholar
  6. [6]
    J. B. Shi, C. Tomasi. Good features to track. In Proceedings of Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, 593–600, 1994. DOI:  https://doi.org/10.1109/CVPR.1994.323794.Google Scholar
  7. [7]
    J. Li, R. Laganiere, G. Roth. Online estimation of trifocal tensors for augmenting live video. In Proceedings of the 3rd IEEE and ACM International Symposium on Mixed and Augmented Reality, IEEE, Arlington, USA, 182–190, 2004. DOI:  https://doi.org/10.1109/ISMAR.2004.42.Google Scholar
  8. [8]
    M. L. Yuan, S. K. Ong, A. Y. C. Nee. Registration using natural features for augmented reality systems. IEEE Transactions on Visualization and Computer Graphics, vol. 12, no. 4, pp. 569–580, 2006. DOI:  https://doi.org/10.1109/TVCG.2006.79.CrossRefGoogle Scholar
  9. [9]
    B. Kang, P. Ren. Natural texture-based tracking algorithm for augmented reality. Systems Engineering and Electronics, vol. 31, no. 10, pp. 2480–2484, 2009. DOI:  https://doi.org/10.3321/j.issn:1001-506X.2009.10.0440. (in Chinese)Google Scholar
  10. [10]
    Y. Hao, Z. J. Xu, Y. Liu, J. Wang, J. L. Fan. Effective Crowd Anomaly Detection Through Spatio-temporal Texture Analysis. International Journal of Automation and Computing, vol. 16, no. 1, pp. 27–39, 2019. DOI:  https://doi.org/10.1007/s11633-018-1141-z.CrossRefGoogle Scholar
  11. [11]
    D. G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, vol. 60, no. 2, pp. 91–110, 2004. DOI:  https://doi.org/10.1023/B:VISI.0000029664.99615.94.CrossRefGoogle Scholar
  12. [12]
    M. Ozuysal, M. Calonder, V. Lepetit, P. Fua. Fast keypoint recognition using random ferns. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 3, pp. 448–461, 2010. DOI:  https://doi.org/10.1109/TPAMI.2009.23.CrossRefGoogle Scholar
  13. [13]
    V. Lepetit, J. Pilet, P. Fua. Point matching as a classification problem for fast and robust object pose estimation. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, Washington DC, USA, pp. 244–250, 2004. DOI:  https://doi.org/10.1109/CVPR.2004.1315170.Google Scholar
  14. [14]
    Y. Zhao, J. J. Li, H. P. Li, D. Yang. Real-time tracking and registration algorithm of scenarios of augmented reality based on improved random fern. Journal of Northeastern University (Natural Science), vol. 37, no. 5, pp. 614–618, 2016. DOI:  https://doi.org/10.3969/j.issn.1005-3026.2016.05.002. (in Chinese)Google Scholar
  15. [15]
    C. H. Yang, S. D. Liu, Z. M. Wang, Y. F. Guo, H. Li. Real-time vehicle matching based on random ferns. Journal of Xiamen University (Natural Science), vol. 53, no. 2, pp. 206–211, 2014. DOI:  https://doi.org/10.6043/j.issn.0438-0479.2014.02.011. (in Chinese)CrossRefGoogle Scholar
  16. [16]
    M. Villamizar, J. Andrade-Cetto, A. Sanfeliu, F. Moreno-Noguer. Bootstrapping boosted random ferns for discriminative and efficient object classification. Pattern Recognition, vol. 45, no. 9, pp. 3141–3153, 2012. DOI:  https://doi.org/10.1016/j.patcog.2012.03.025.CrossRefGoogle Scholar
  17. [17]
    Y. Liu, D. G. Xi, Z. L. Li, Y. Hong. A new methodology for pixel-quantitative precipitation nowcasting using a pyramid Lucas Kanade optical flow approach. Journal of Hydrology, vol. 529, pp. 354–364, 2015. DOI:  https://doi.org/10.1016/j.jhydrol.2015.07.042.CrossRefGoogle Scholar
  18. [18]
    T. D. Chen, J. Hu, D. Wu. Dynamic target detection and tracking based on fast computation using sparse optical flow. Journal of Image and Graphics, vol. 18, no. 12, pp. 1593–1600, 2013. DOI:  https://doi.org/10.11834/jig.20131207. (in Chinese)Google Scholar
  19. [19]
    Y. Xie, X. D. Yang, Z. Liu, S. N. Ren, K. Chen. Method for visual localization of oil and gas wellhead based on distance function of projected features. International Journal of Automation and Computing, vol. 14, no. 2, pp. 147–158, 2017. DOI:  https://doi.org/10.1007/s11633-017-1063-1.CrossRefGoogle Scholar
  20. [20]
    J. S. Xu, Y. J. Wang, X. Cheng, S. Li, S. Y. Chen. Adaptive method for homography matrix estimation. Computer Engineering and Applications, vol. 52, no. 5, pp. 160–164, 2016. DOI:  https://doi.org/10.3778/j.issn.1002-8331.1409-0357. (in Chinese)Google Scholar
  21. [21]
    J. Lin, Y. T. Wang, Y. Liu, K. Yang. Real-time markerless registration algorithm for augmented reality based on template tracking. Journal of Image and Graphics, vol. 13, no. 9, pp. 1812–1819, 2008. DOI:  https://doi.org/10.11834/jig.20080929. (in Chinese)Google Scholar
  22. [22]
    A. T. Erdem, A. O. Ercan. Fusing inertial sensor data in an extended Kalman filter for 3D camera tracking. IEEE Transactions on Image Processing, vol. 24, no. 2, pp. 538–548, 2015. DOI:  https://doi.org/10.1109/TIP.2014.2380176.MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Institute of Automation, Chinese Academy of Sciences and Springer-Verlag Gmbh Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Lanzhou Institute of PhysicsChina Academy of Space TechnologyLanzhouChina

Personalised recommendations