Advertisement

The Automatic Classification 3D Point Clouds Based Associative Markov Network Using Context Information

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 107)

Abstract

Many applications of mobile mapping want to automatic classification point clouds into different classes for further processing. In this chapter we present a new approach for labeling 3D point clouds with using a novel feature descriptor—the four directions scan line gradient, and context classification models—associative Markov network (AMN). To build informative and robust 3D feature point representations, our descriptors encode the underlying surface geometry around a point using multi-scanlines gradients. It is more stable and reliable than normal vectors in urban environments with wide variety of natural and manmade objects. By defining objects models of 3D geometric surfaces and making use of contextual information of AMN, our system is able to successfully segment and label 3D point clouds. We use FC09 datasets to evaluate the proposed algorithm.

Keywords

3D point clouds Associative Markov network Four directions scan line gradient 

Notes

Acknowledgments

National Natural Science Foundation of China under Grant No. 41050110437,41001306.

“Remote Collaboration Office Management Information System” Science and Technology Project of Henan Electric Power Company (2010 Batch 1 Class 3 Item 14).

References

  1. 1.
    Montemerlo M, Becker J, Bhat S, Dahlkamp H, Dolg D, Ettinger S, Haehnel D (2008) Junior: the stanford entry in the urban challenge. J Field Robot 25(9):569–597 CCrossRefGoogle Scholar
  2. 2.
    Lalonde J-F, Vandapel N, Hebert M (2007) Data structures for efficient dynamic processing in 3-d. Int J Robot Res 26(8):777–796CrossRefGoogle Scholar
  3. 3.
    Taskar B, Chatalbashev V, Koller D (2004) Learning associative Markov networks. In: Twenty first international conference on machine learningGoogle Scholar
  4. 4.
    Alexa M, Adamson A (2004) On normals and projection operators for surfaces defined by point sets. In: Proceedings of symposium on point-based graphics, pp 149–155Google Scholar
  5. 5.
    Mitra NJ, Nguyen A (2003) Estimating surface normals in noisy point cloud data. In: SCG’03: Proceedings of the nineteenth annual symposium on computational geometry, pp 322–328Google Scholar
  6. 6.
    Burel G, H′enocq H (1995) Three-dimensional invariants and their application to object recognition. Signal Process 45(1):1–22CrossRefMATHGoogle Scholar
  7. 7.
    Gelfand N, Mitra NJ, Guibas LJ, Pottmann H (2005) Robust global egistration. In: Proceedings of symposium on geometric processingGoogle Scholar
  8. 8.
    Anguelov D, Taskar B, Chatalbashev V, Koller D, Gupta D, Heitz G, Ng A (2005) Discriminative learning of Markov random fields for segmentation of 3d scan data. In: Proceedings of the conference on computer vision and pattern recognition (CVPR) pp 169–176Google Scholar
  9. 9.
    Frome A, Huber D, Kolluri R, Bulow T, Malik J (2004) Recognizing objects in range data using regional point descriptors. In: Proceedings of ECCVGoogle Scholar
  10. 10.
    Limketkai B, Liao L, Fox D (2005) Relational object maps for mobile robots. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), pp 1471–1476Google Scholar
  11. 11.
    Anguelov D, Taskar B, Chatalbashev V, Koller D, Gupta D, Heitz G, Ng A (2005) Discriminative learning of markov random fields for segmentation of 3d scan data. In: Proceedings of the conference on computer vision and pattern recognition (CVPR), pp 169–176Google Scholar
  12. 12.
    Meltzer T, Yanover C, Weiss Y (2005) Globally optimal solutions for energy minimization in stereo vision using reweighted belief propagation. In: ICCV pp 428–435Google Scholar
  13. 13.
    Kolmogorov V (2006) Convergent tree-reweighted message passing for energy minimization. PAMI 28(10):1568–1583Google Scholar
  14. 14.
    Kohli P, Kumar M, Torr P (2007) P3 & beyond: solving energies with higher order cliques. In: CVPRGoogle Scholar
  15. 15.
    Boykov Y, Veksler O, Zabih R, Fast approximate energy minimization via graph cut, IEEE Transactions on 23:1222–1239Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  • Gang Wang
    • 1
  • Ming Li
    • 2
  • TingTing Zhou
    • 3
  • Longgang Chen
    • 1
  1. 1.Henan Electric Power Survey and Design InstituteZhengzhouChina
  2. 2.School of Computer ScienceWuhan UniversityWuhanChina
  3. 3.Power and Mechanical CollegeWuhan UniversityWuhanChina

Personalised recommendations