SIFT Based Monocular SLAM with GPU Accelerated

  • Tonghui Wang
  • Guoyun Lv
  • Shikai Wang
  • Haili Li
  • Baicen Lu
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 237)


With the rapid development of computer vision technology, 3D Reconstruction based on monocular SLAM (Simultaneous Localization and Mapping) has got more and more attention for its simple requirements, low cost, easy to implement, convenient to carry. ORB-SLAM is a kind of monocular SLAM method based on feature point. ORB feature can meet the real-time requirements for SLAM, but it does not have scale invariance. In this paper, we proposed a monocular SIFT-SLAM, in which a SIFT (Scale Invariant Feature Transform) algorithm based on GPU is used to replace the ORB algorithm, to implement 3D Reconstruction. We show the experiment result of SIFT-SLAM in this paper, which gets some improvement.


SLAM Monocular SIFT GPU 3D Reconstruction 



This work is sponsored by the Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University (No. Z2017139).


  1. 1.
    Smith, R., Self, M., Chessman, P.: Estimating uncertain spatial relationships in robotics. In: Proceedings of the Uncertainty in Artificial Intelligence (1988)Google Scholar
  2. 2.
    Davison, A.J., Nobuyuki, K.: 3D simultaneous localization and map building using active vision for a robot moving on undulating terrain. In: Proceedings of the IEEE International Conference on Computer Vision and Recognization, Huwaii, pp. 384–391 (2001)Google Scholar
  3. 3.
    Andersen, D.R., Cuykendall, R., Regan, J.J.: SLAM - vectorized calculation of refraction and reflection for a Gaussian beam at a nonlinear interface in the presence of a diffusive Kerr-like nonlinearity. Comput. Phys. Commun. 48(2), 255–264 (1988)CrossRefGoogle Scholar
  4. 4.
    Engel, J., Schöps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834–849. Springer, Cham (2014). Scholar
  5. 5.
    Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Robot. 31(5), 1147–1163 (2015)CrossRefGoogle Scholar
  6. 6.
    Rublee, E., Rabaud, V., Konolige, K.: ORB: an efficient alternative to SIFT or SURF. In: Proceedings, vol. 58, no. 11, pp. 2564–2571 (2011)Google Scholar
  7. 7.
    Lowe, D.G.: Distinctive image features from scale-invariant key-points. J. Comput. Vis. 2(60), 91–110 (2004)CrossRefGoogle Scholar
  8. 8.
    Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, NY, USA, pp. 2161–2168 (2006)Google Scholar
  9. 9.
    Kümmerle, R., Grisetti, G., Strasdat, H., Konolige, K., Burgard, W.: g2o: a general framework for graph optimization. In: International Conference on Robotics and Automation (ICRA) (2011)Google Scholar
  10. 10.
    Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: Proceedings of the IEEE and ACM International Symposium on Mixed and Augmented Reality, Nara, Japan, pp. 225–234 (2007)Google Scholar
  11. 11.
    Klein, G., Murray, D.: Improving the agility of keyframe-based SLAM. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 802–815. Springer, Heidelberg (2008). Scholar
  12. 12.
    Mur Artal, R., Tardos, J.D.: Fast relocalisastion and loop closing in keyframe-based SLAM. In: Proceedings of the IEEE International Conference on Robotics and Automation, New Orleans, LA, pp. 846–853 (2014)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  • Tonghui Wang
    • 1
  • Guoyun Lv
    • 1
  • Shikai Wang
    • 1
  • Haili Li
    • 1
  • Baicen Lu
    • 1
  1. 1.School of Electronics and InformationNorthwestern Polytechnical UniversityXi‘anChina

Personalised recommendations