Robust and Accurate Line- and/or Point-Based Pose Estimation without Manhattan Assumptions

  • Yohann Salaün
  • Renaud Marlet
  • Pascal Monasse
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9911)


Usual Structure from Motion techniques based on feature points have a hard time on scenes with little texture or presenting a single plane, as in indoor environments. Line segments are more robust features in this case. We propose a novel geometrical criterion for two-view pose estimation using lines, that does not assume a Manhattan world. We also define a parameterless (a contrario) RANSAC-like method to discard calibration outliers and provide more robust pose estimations, possibly using points as well when available. Finally, we provide quantitative experimental data that illustrate failure cases of other methods and that show how our approach outperforms them, both in robustness and precision.


Motion Estimation Building Information Model Line Pair Structure From Motion Trifocal Tensor 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work was carried out in IMAGINE, a joint research project between ENPC and CSTB. It was partly supported by Bouygues Construction.

Supplementary material

419982_1_En_49_MOESM1_ESM.pdf (13.4 mb)
Supplementary material 1 (pdf 13737 KB)


  1. 1.
    Xu, Y., Oh, S., Hoogs, A.: A minimum error vanishing point detection approach for uncalibrated monocular images of man-made environments. In: IEEE Computer Vision and Pattern Recognition (CVPR 2013), pp. 1376–1383, June 2013Google Scholar
  2. 2.
    Lezama, J., Grompone von Gioi, R., Randall, G., Morel, J.M.: Finding vanishing points via point alignments in image primal and dual domains. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), June 2014Google Scholar
  3. 3.
    Elqursh, A., Elgammal, A.: Line-based relative pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011), pp. 3049–3056, June 2011Google Scholar
  4. 4.
    Weng, J., Huang, T.S., Ahuja, N.: Motion and structure from line correspondences; closed-form solution, uniqueness, and optimization. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI 1992) 14(3), 318–336 (1992)CrossRefGoogle Scholar
  5. 5.
    Zhang, Z.: Estimating motion and structure from correspondences of line segments between two perspective images. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI 1995) 17(12), 1129–1139 (1995)CrossRefGoogle Scholar
  6. 6.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, New York (2004). ISBN: 0521540518CrossRefzbMATHGoogle Scholar
  7. 7.
    Bartoli, A., Sturm, P.F.: Structure-from-motion using lines: representation, triangulation, and bundle adjustment. Comput. Vis. Image Underst. (CVIU 2005) 100(3), 416–441 (2005)CrossRefGoogle Scholar
  8. 8.
    Schindler, G., Krishnamurthy, P., Dellaert, F.: Line-based structure from motion for urban environments. In: Proceedings of the 3rd International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT 2006), Computer Society, pp. 846–853. IEEE, Washington, DC (2006)Google Scholar
  9. 9.
    Zhang, L., Koch, R.: Structure and motion from line correspondences: representation, projection, initialization and sparse bundle adjustment. J. Vis. Commun. Image Representation 25(5), 904–915 (2014)CrossRefGoogle Scholar
  10. 10.
    Chandraker, M., Lim, J., Kriegman, D.: Moving in stereo: efficient structure and motion using lines. In: IEEE 12th International Conference on Computer Vision (ICCV 2009), pp. 1741–1748 (2009)Google Scholar
  11. 11.
    Pradeep, V., Lim, J.: Egomotion using assorted features. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010), pp. 1514–1521, June 2010Google Scholar
  12. 12.
    Koseck, J., Zhang, W.: Extraction, matching, and pose recovery based on dominant rectangular structures. Comput. Vis. Image Underst. (CVIU 2005) 100(3), 274–293 (2005)CrossRefGoogle Scholar
  13. 13.
    Montiel, J., Tardós, J., Montano, L.: Structure and motion from straight line segments. Pattern Recogn. (PR 2000) 33(8), 1295–1307 (2000)CrossRefGoogle Scholar
  14. 14.
    Bay, H., Ferrari, V., Van Gool, L.: Wide-baseline stereo matching with line segments. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2005), Computer Society, pp. 329–336. IEEE, Washington, DC (2005)Google Scholar
  15. 15.
    Draréni, J., Keriven, R., Marlet, R.: Indoor calibration using segment chains. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 71–80. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-23123-0_8 CrossRefGoogle Scholar
  16. 16.
    Lee, J.K., Yoon, K.J.: Real-time joint estimation of camera orientation and vanishing points. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), June 2015Google Scholar
  17. 17.
    Cipolla, R., Drummond, T., Robertson, D.: Camera calibration from vanishing points in images of architectural scenes. In: British Machine Vision Conference (BMVC 1999), pp. 382–391 (1999)Google Scholar
  18. 18.
    Rother, C., Carlsson, S.: Linear multi view reconstruction and camera recovery using a reference plane. Int. J. Comput. Vis. (IJCV 2002) 49(2–3), 117–141 (2002)CrossRefzbMATHGoogle Scholar
  19. 19.
    Sinha, S.N., Steedly, D., Szeliski, R.: A multi-stage linear approach to structure from motion. In: Kutulakos, K.N. (ed.) ECCV 2010. LNCS, vol. 6554, pp. 267–281. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-35740-4_21 Google Scholar
  20. 20.
    Markley, F.L.: Attitude determination using vector observations and the singular value decomposition. J. Astronaut. Sci. 36(3), 245–258 (1988)MathSciNetGoogle Scholar
  21. 21.
    Schönemann, P.: A generalized solution of the orthogonal Procrustes problem. Psychometrika 31(1), 1–10 (1966)MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Nistér, D.: An efficient solution to the five-point relative pose problem. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI 2004) 26(6), 756–777 (2004)CrossRefGoogle Scholar
  23. 23.
    Moulon, P., Monasse, P., Marlet, R.: Adaptive structure from motion with a Contrario model estimation. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7727, pp. 257–270. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-37447-0_20 CrossRefGoogle Scholar
  24. 24.
    Moisan, L., Stival, B.: A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix. Int. J. Comput. Vis. (IJCV 2004) 57(3), 201–218 (2004)CrossRefGoogle Scholar
  25. 25.
    Moisan, L., Moulon, P., Monasse, P.: Fundamental matrix of a stereo pair, with a contrario elimination of outliers. Image Process. On Line (IPOL) 6, 89–113 (2016). MathSciNetCrossRefGoogle Scholar
  26. 26.
    Moisan, L., Moulon, P., Monasse, P.: Automatic homographic registration of a pair of images, with a contrario elimination of outliers. Image Process. On Line (IPOL) 2, 56–73 (2012). CrossRefGoogle Scholar
  27. 27.
    Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008). pp. 1–8, June 2008Google Scholar
  28. 28.
    von Gioi, R.G., Jakubowicz, J., Morel, J.M., Randall, G.: LSD: a line segment detector. Image Process. On Line (IPOL 2012) 2, 35–55 (2012). doi: 10.5201/ipol.2012.gjmr-lsd CrossRefGoogle Scholar
  29. 29.
    Salaün, Y., Marlet, R., Monasse, P.: Multiscale line segment detector for robust and accurate SfM. In: 23rd International Conference on Pattern Recognition (ICPR) (2016)Google Scholar
  30. 30.
    Zhang, L., Koch, R.: An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency. J. Vis. Commun. Image Representation 24(7), 794–805 (2013)CrossRefGoogle Scholar
  31. 31.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. (IJCV 2004) 60(2), 91–110 (2004)CrossRefGoogle Scholar
  32. 32.
    Liu, Z., Marlet, R.: Virtual line descriptor and semi-local matching method for reliable feature correspondence. In: British Machine Vision Conference (BMVC 2012), United Kingdom, pp. 16.1–16.11, September 2012Google Scholar
  33. 33.
    Almansa, A., Desolneux, A., Vamech, S.: Vanishing point detection without any a priori information. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI 2003) 25(4), 502–507 (2003)CrossRefGoogle Scholar
  34. 34.
    Agarwal, S., Mierle, K. et al.: Ceres solver.

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Yohann Salaün
    • 1
    • 2
  • Renaud Marlet
    • 1
  • Pascal Monasse
    • 1
  1. 1.LIGM, UMR 8049, École des PontsUPEChamps-sur-marneFrance
  2. 2.CentraleSupélecChâtenay-MalabryFrance

Personalised recommendations