Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Camera pose estimation based on global structure from motion

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In this paper, a new global camera pose estimation algorithm WTLS-IRLS is proposed, which can effectively solve the global rotation when there are outliers. Firstly, according to the relationship between the rotation vector and the rotation matrix, we simplify the product operation of the rotation matrix into the subtraction operation of the rotation vector, which reduces the complexity of the algorithm. Secondly, the weighted total least squares (WTLS) and the iteratively reweighted least squares (IRLS) are used to average relative rotations. As the initialization of IRLS, WTLS provides a good initial guess by correcting the linearization equation and adding weight information to the relative rotations. IRLS continues to add weight information to the relative rotation matrices to optimize the global rotations. We demonstrate the performance of our approach by a number of large-scale data sets, the results show that our method has been greatly improved in efficiency, accuracy and iteration. In order to verify the correctness of our proposed method, we completed the complete reconstruction process, the experimental results show that our proposed WTLS-IRLS rotation averaging algorithm can obtain dense point clouds with more three-dimensional points.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Aftab K, Hartley R, Trumpf J (2015) Generalized weiszfeld algorithms for lq optimization. IEEE Trans Pattern Anal Mach Intell (TPAMI) 37(4):728–745

    Article  Google Scholar 

  2. Arrigoni F, Magri L, Rossi B, et al (2014) Robust absolute rotation estimation via low-rank and sparse matrix decomposition. Int Conf 3D Vis (3DV):491-498

  3. Cao M, Li S, Jia W, Li S, Liu X (2017) Robust bundle adjustment for large-scale structure from motion. Multimed Tools Appl (MTA) 76(21):21843–21867

    Article  Google Scholar 

  4. Chatterjee A, Govindu VM (2013) Efficient and robust large-scale rotation averaging. IEEE Int Conf Comput Vis (ICCV):521-528

  5. Chatterjee A, Govindu VM (2018) Robust relative rotation averaging. IEEE Trans Pattern Anal Mach Intell (TPAMI) 40(4):958–972

    Article  Google Scholar 

  6. Crandall D, Owens A, Snavely N, et al (2011) Discrete-continuous optimization for large-scale structure from motion. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):3001-3008

  7. Cui Z, Tan P (2015) Global structure-from-motion by similarity averaging. IEEE Int Conf Comput Vis (ICCV):864-872

  8. Cui H, Shen S, Hu Z (2016) Robust global translation averaging with feature tracks. Int Conf Pattern Recogn (ICPR):3727-3732

  9. Dapeng C, Yongqin Z, Zhongyu L et al (2017) Weighted motion averaging for the registration of multi-view range scans. Multimed Tools Appl (MTA) 77(9):10651–10668

    Google Scholar 

  10. Furukawa Y , Curless B , Seitz SM , et al (2010) Towards internet-scale multi-view stereo. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):1434-1441

  11. Govindu VM (2001) Combining two-view constraints for motion estimation. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):218-225

  12. Govindu VM (2004) Lie-algebraic averaging for globally consistent motion estimation. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):684-691

  13. Govindu VM (2006) Robustness in motion averaging. Asian Conf Comput Vis (ACCV):457–466

  14. Hartley R, Aftab K, and Trumpf J (2011) L1 rotation averaging using the weiszfeld algorithm. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):3041–3048

  15. Huang X, Liang Z, Zhou X, et al. (2019). Learning transformation synchronization. IEEE Int Conf Comput Vis Pattern Recogn (CVPR): 8082-8091.

  16. Ke F, Xie J, Chen Y, et al (2014) Globally optimal estimates for rotation averaging problems. Intell Hum Mach Syst Cybern (IHMSC):309–312

  17. Li H, Hartley R (2006) Five-point motion estimation made easy. Int Conf Pattern Recogn (ICPR):630-633

  18. Long G, Kneip L, Li X, et al (2015) Simplified mirror-based camera pose computation via rotation averaging. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):1247-1255

  19. Nistér D (2004) An efficient solution to the five-point relative pose problem. IEEE Trans Pattern Anal Mach Intell (TPAMI) 26(6):756–770

    Article  Google Scholar 

  20. Roberts R, Sinha SN, Szeliski R, et al (2011) Structure from motion for scenes with large duplicate structures. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):3137-3144

  21. Snavely N, Seitz SM, Szeliski R (2007) Modeling the world from internet photo collections. Int J Comput Vis (IJCV) 80(2):189–210

    Article  Google Scholar 

  22. Toldo R, Gherardi R, Farenzena M, Fusiello A (2015) Hierarchical structure-and-motion recovery from uncalibrated images. Comput Vis Image Underst 140(3):127–143

    Article  Google Scholar 

  23. Torr PHS, Zisserman A (1997) Robust parameterization and computation of the trifocal tensor. Image Vis Comput 15(8):591–605

    Article  Google Scholar 

  24. Tron R, Vidal R (2011) Distributed computer vision algorithms through distributed averaging. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):57-63

  25. Tron R, Vidal R, and Terzis A (2008) Distributed pose averaging in camera networks via consensus on SE (3). Int Conf Distrib Smart Cameras (ICDSC):1-10

  26. Wang X, Rottensteiner F, Heipke C (2019) Structure from motion for ordered and unordered image sets based on random kd forests and global pose estimation. ISPRS J Photogramm Remote Sens 147:19–41

    Article  Google Scholar 

  27. Wilson K, Snavely N (2014) Robust global translations with 1DSfM. Eur Conf Comput Vis (ECCV):61–75

  28. Wu C (2013) Towards Linear-Time Incremental Structure from Motion. Int Conf 3D Vis (3DV) Seattle:127–134

  29. Wu C, Agarwal S, Curless B, et al (2011) Multicore bundle adjustment. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):3057-3064

  30. Zach C, Klopschitz M, Pollefeys M (2010) Disambiguating visual relations using loop constraints. IEEE Int Conf Comput Vis Pattern Recogn (CVPR):1426-1433

Download references

Acknowledgments

This work is supported by National Natural Science Foundation of China (No. 61502185 and U1536203) and the Fundamental Research Funds for the Central Universities (No: 2017KFYXJJ071).

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China

    Dan Li, Danya Song, Shuang Liu, Junwen Ji, Kang Zeng, Yingsong Hu & Hefei Ling

Authors
  1. Dan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Danya Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shuang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Junwen Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kang Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yingsong Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hefei Ling
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shuang Liu.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, D., Song, D., Liu, S. et al. Camera pose estimation based on global structure from motion. Multimed Tools Appl 79, 23223–23242 (2020). https://doi.org/10.1007/s11042-020-09045-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-09045-8

Keywords

Search

Navigation