Advertisement

Detection of Clustered Objects in Sparse Point Clouds Through 2D Classification and Quadric Filtering

  • Christopher Herbon
  • Benjamin Otte
  • Klaus Tönnies
  • Bernd Stock
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8753)

Abstract

A novel approach for detecting single objects in large clusters is presented. The proposed method is designed to work with structure from motion data, which typically includes a set of input images, a very sparse point cloud and camera poses. We use provided objects of interest from 2D classification, which are then projected to three dimensional space.

The main contribution of this paper is an algorithm, which accurately detects the objects of interest and approximates their locations in three dimensional space, by using 2D classification data and quadric filtering. Optionally, a partly dense reconstructed mesh, containing objects of interest only, is computed, without the need for applying patch based multiple view stereo algorithms first. Experiments are performed on a challenging database containing images of wood log piles with a known ground truth number of objects, provided by timber processing companies. The average true positive rate exceeds 98.0 % in every case, while it is shown how to reduce the false positive rate to less than 0.5 %.

Keywords

Point Cloud Object Detection Local Binary Pattern Structure From Motion Positive Detection Rate 
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.

References

  1. 1.
    Banerjee, J., Moelker, A., Niessen, W.J., van Walsum, T.: 3D LBP-based rotationally invariant region description. In: Park, J.-I., Kim, J. (eds.) ACCV Workshops 2012, Part I. LNCS, vol. 7728, pp. 26–37. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  2. 2.
    Bao, S.Y., Savarese, S.: Semantic structure from motion. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, pp. 2025–2032. IEEE (2011)Google Scholar
  3. 3.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  4. 4.
    Brown, M., Lowe, D.G.: Automatic panoramic image stitching using invariant features. Int. J. Comput. Vis. 74(1), 59–73 (2007)CrossRefGoogle Scholar
  5. 5.
    Buch, N., Orwell, J., Velastin, S.A.: 3D extended histogram of oriented gradients (3DHOG) for classification of road users in urban scenes. In: British Machine Vision Association (BMVC) (2009)Google Scholar
  6. 6.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893. June 2005Google Scholar
  7. 7.
    Fehr, J., Burkhardt, H.: 3D rotation invariant local binary patterns. In: ICPR, Citeseer, pp. 1–4 (2008)Google Scholar
  8. 8.
    Fei-Fei, L., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 524–531. IEEE (2005)Google Scholar
  9. 9.
    Fink, F.: Foto-optische Erfassung der Dimension von Nadelrundholzabschnitten unter Einsatz digitaler, bildverarbeitender Methoden. Ph.D. thesis, Albert-Ludwigs-Universitt (2004)Google Scholar
  10. 10.
    Furukawa, Y., Ponce, J.: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intel. 32(8), 1362–1376 (2010)CrossRefGoogle Scholar
  11. 11.
    Gutzeit, E., Ohl, S., Kuijper, A., Voskamp, J., Urban, B.: Setting graph cut weights for automatic foreground extraction in wood log images. In: VISAPP (2), pp. 60–67 (2010)Google Scholar
  12. 12.
    Gutzeit, E., Ohl, S., Voskamp, J., Kuijper, A., Urban, B.: Automatic wood log segmentation using graph cuts. In: Richard, P., Braz, J. (eds.) VISIGRAPP 2010. CCIS, vol. 229, pp. 96–109. Springer, Heidelberg (2011)Google Scholar
  13. 13.
    Gutzeit, E., Voskamp, J.: Automatic segmentation of wood logs by combining detection and segmentation. In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Fowlkes, C., Wang, S., Choi, M.-H., Mantler, S., Schulze, J., Acevedo, D., Mueller, K., Papka, M. (eds.) ISVC 2012, Part I. LNCS, vol. 7431, pp. 252–261. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  14. 14.
    Herbon, C., Tönnies, K., Stock, B.: Adaptive planar and rotational image stitching for mobile devices. In: Proceedings of the 5th ACM Multimedia Systems Conference, pp. 213–223. ACM (2014)Google Scholar
  15. 15.
    Herbon, C., Tönnies, K., Stock, B.: Detection and segmentation of clustered objects by using iterative classification, segmentation, and Gaussian mixture models and application to wood log detection. In: 36th German Conference on Pattern Recognition, Münster, 2–5 September 2014Google Scholar
  16. 16.
    Khan, S.M.: Multi-view Approaches to Tracking, 3D Reconstruction and Object Class Detection. Ph.D. thesis, University of Central Florida (2008)Google Scholar
  17. 17.
    Lewis, J.: Fast template matching. Vis. Interface 95, 15–19 (1995)Google Scholar
  18. 18.
    Liu, K., Skibbe, H., Schmidt, T., Blein, T., Palme, K., Ronneberger, O.: 3D rotation-invariant description from tensor operation on spherical HOG field. NeuroImage 57(2), 416–422 (2011)CrossRefGoogle Scholar
  19. 19.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, vol. 2, pp. 1150–1157. IEEE (1999)Google Scholar
  20. 20.
    Molton, N., Davison, A.J., Reid, I.: Locally planar patch features for real-time structure from motion. In: BMVC, pp. 1–10 (2004)Google Scholar
  21. 21.
    Moulon, P., Monasse, P., Marlet, R., et al.: Global fusion of relative motions for robust, accurate and scalable structure from motion. In: Proceedings of IEEE International Conference on Computer Vision (2013)Google Scholar
  22. 22.
    Ojala, T., Pietikainen, M., Harwood, D.: Performance evaluation of texture measures with classification based on kullback discrimination of distributions. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994, vol. 1, pp. 582–585 (1994)Google Scholar
  23. 23.
    Okamoto Jr., J., Grassi Jr., V.: Visual servo control of a mobile robot using omnidirectional vision. In: Proceedings of Mechatronics, pp. 413–422 (2002)Google Scholar
  24. 24.
    Scherer, M., Walter, M., Schreck, T.: Histograms of oriented gradients for 3d object retrieval. In: Proceedings of the WSCG, pp. 41–48 (2010)Google Scholar
  25. 25.
    Skibbe, H., Reisert, M., Burkhardt, H.: SHOG - spherical HOG descriptors for rotation invariant 3D object detection. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 142–151. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  26. 26.
    Szeliski, R.: Image alignment and stitching: a tutorial. Found. Trends Comput. Graph. Vis. 2(1), 1–104 (2006)CrossRefGoogle Scholar
  27. 27.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001. vol. 1, pp. I-511-I-518 (2001)Google Scholar
  28. 28.
    Wang, B., Liang, W., Wang, Y., Liang, Y.: Head pose estimation with combined 2D sift and 3D HOG features. In: Seventh International Conference on Image and Graphics (ICIG 2013), pp. 650–655 July 2013Google Scholar
  29. 29.
    Yang, J., Liang, W., Jia, Y.: Face pose estimation with combined 2D and 3D HOG features. In: 21st International Conference on Pattern Recognition (ICPR), 2012, pp. 2492–2495 (2012)Google Scholar
  30. 30.
    Zwillinger, D.: CRC Standard Mathematical Tables and Formulae, 32nd Edn., Discrete Mathematics and Its Applications, CRC Press (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Christopher Herbon
    • 1
  • Benjamin Otte
    • 1
  • Klaus Tönnies
    • 2
  • Bernd Stock
    • 1
  1. 1.HAWK Fakultät Naturwissenschaften und TechnikGöttingenGermany
  2. 2.Institut für Simulation und GraphikOtto-von-Guericke-Universität MagdeburgMagdeburgGermany

Personalised recommendations