International Journal of Computer Vision

, Volume 99, Issue 2, pp 232–255 | Cite as

3D Geometric Scale Variability in Range Images: Features and Descriptors

  • Prabin Bariya
  • John Novatnack
  • Gabriel Schwartz
  • Ko Nishino
Article

Abstract

Despite their ubiquitous presence, little has been investigated about the scale variability—the relative variations in the spatial extents of local structures—of 3D geometric data. In this paper we present a comprehensive framework for exploiting this 3D geometric scale variability in range images that provides rich information for characterizing the overall geometry. We derive a sound scale-space representation, which we refer to as the geometric scale-space, that faithfully encodes the scale variability of the surface geometry, and derive novel detectors to extract prominent features and identify their natural scales. The result is a hierarchical set of features of different scales which we refer to as scale-dependent geometric features. We then derive novel local shape descriptors that represent the surface structures that give rise to those features by carving out and encoding the local surface that fall within the support regions of the features. This leads to scale-dependent or scale-invariant local shape descriptors that convey significant discriminative information of the object geometry. We demonstrate the effectiveness of geometric scale analysis on range images, and show that it enables novel applications, in particular, fully automatic registration of multiple objects from a mixed set of range images and 3D object recognition in highly cluttered range image scenes.

Keywords

Range image Scale variability Scale-space Geometric feature Shape descriptor Range image registration 3D object recognition 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Akagunduz, E., & Ulusoy, I. (2007). Extraction of 3D transform and scale invariant patches from range scans. In IEEE int’l conf. on computer vision and pattern recognition (pp. 1–8). CrossRefGoogle Scholar
  2. Bariya, P., & Nishino, K. (2010). Scale-hierarchical 3D object recognition in cluttered scenes. In IEEE conf. on computer vision and pattern recognition. Google Scholar
  3. Brady, M., Ponce, J., Yuille, A., & Asada, H. (1985). Describing surfaces (Technical Report AIM-822). MIT Aritificial Intelligence Laboratory Memo. Google Scholar
  4. Bro, R., Acar, E., & Kolda, T. G. (2008). Resolving the sign ambiguity in the singular value decomposition. Journal of Chemometrics 22, 135–140. CrossRefGoogle Scholar
  5. Carmo, M. P. D. (1976). Differential geometry of curves and surfaces. Prentice Hall: New York. MATHGoogle Scholar
  6. Chang, K. C., Ding, W., & Ye, R. (1992). Finite-time blow-up of the heat flow of harmonic maps from surfaces. Journal of Differential Geometry, 36(2), 507–515. MathSciNetMATHGoogle Scholar
  7. Chen, C., Hung, Y., & Cheng, J. (1999). RANSAC-based DARCES: a new approach to fast automatic registration of partially overlapping range images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(11), 1229–1234. CrossRefGoogle Scholar
  8. Chua, C., & Jarvis, R. (1997). Point signatures: a new representation for 3D object recognition. International Journal of Computer Vision, 25(1), 63–85. CrossRefGoogle Scholar
  9. Cohen, R., Hardt, R., Kinderlehrer, D., Lin, S., & Luskin, M. (1987). Minimum energy configurations for liquid crystals: computational results (pp. 99–121). New York: Springer. Google Scholar
  10. Coron, J. M. (1990). Nonuniqueness for the heat flow of harmonic maps. Annales de l’Institut Heri Poincaré, 7(4), 335–344. MathSciNetMATHGoogle Scholar
  11. Dinh, H. Q., & Kropac, S. (2006). Multi-resolution spin-images. In IEEE int’l conf. on computer vision and pattern recognition, Washington, DC, USA (pp. 863–870). Los Alamitos: IEEE Comput. Soc. Google Scholar
  12. Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381–395. MathSciNetCrossRefGoogle Scholar
  13. Flynn, P., & Jain, A. (1991). Bonsai: 3D object recognition using constrained search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(10), 1066–1075. CrossRefGoogle Scholar
  14. Freire, A. (1995). Uniqueness for the harmonic map flow in two dimensions. Calculus of Variations and Partial Differential Equations, 3(1), 95–105. MathSciNetMATHCrossRefGoogle Scholar
  15. Frome, A., Huber, D., Kolluri, R., Bulow, T., & Malik, J. (2004). Recognizing objects in range data using regional point descriptors. In European conf. on computer vision. Google Scholar
  16. Gelfand, N., Mitra, N., Guibas, L., & Pottmann, H. (2005). Robust global registration. In Symposium on geometry processing. Google Scholar
  17. Grimson, W. (1988). The combinatorics of object recognition in cluttered environments using constrained search. In IEEE int’l conf on computer vision (pp. 218–227). Google Scholar
  18. Grimson, W., Lozano-Perez, T., & Huttenlocher, D. (1990). Object recognition by computer: the role of geometric constraints. Cambridge: MIT Press. Google Scholar
  19. ter Haar, F., & Veltkamp, R. (2007). Automatic multiview quadruple alignment of unordered range scans. In IEEE shape modeling and applications, Washington, DC, USA (pp. 137–146). Los Alamitos: IEEE Comput. Soc. Google Scholar
  20. Hardt, R. (1991). Singularities of harmonic maps. Bulletin of the American Mathematical Society, 34, 15–34. MathSciNetCrossRefGoogle Scholar
  21. Huber, D., & Hebert, M. (2003). Fully automatic registration of multiple 3d data sets. Image and Vision Computing, 21(7), 637–650. CrossRefGoogle Scholar
  22. Johnson, A. (1997). Spin-images: a representation for 3-D surface matching. Ph.D. thesis, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. Google Scholar
  23. Johnson, A., & Hebert, M. (1999). Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(5), 433–449. CrossRefGoogle Scholar
  24. Johnson, A., Carmichael, O., Huber, D., & Hebert, M. (1998). Toward a general 3-D matching engine: multiple models, complex scenes, and efficient data filtering. In Proceedings of the 1998 image understanding workshop (IUW) (pp. 1097–1107). Google Scholar
  25. Kazhdan, M., Bolitho, M., & Hoppe, H. (2006). Poisson surface reconstruction. In Eurographics symp. on geometry processing, Eurographics Association, Aire-la-Ville, Switzerland (pp. 61–70). Google Scholar
  26. Kimmel, R. (1997). Intrinsic scale space for images on surfaces: the geodesic curvature flow. In Scale-space theory in computer vision (pp. 212–223). CrossRefGoogle Scholar
  27. Kimmel, R., & Sethian, JA (1998). Computing geodesic paths on manifolds. In Proceedings of national academy of sciences USA (pp. 8431–8435). Google Scholar
  28. Koenderink, J. (1984). The structure of images. Biological Cybernetics, 50, 363–370. MathSciNetMATHCrossRefGoogle Scholar
  29. Lab QURCV (2009). Queen’s range image and 3-D model database. http://rcvlab.ece.queensu.ca/~qridb/
  30. Lalonde, J., Unnikrishnan, R., Vandapel, N., & Hebert, M. (2005). Scale selection for classification of point-sampled 3-D surfaces. In Int’l conf. on 3-D digital imaging and modeling. Google Scholar
  31. Li, X., & Guskov, I. (2005). Multi-scale features for approximate alignment of point-based surfaces. In Symposium on geometry processing. Google Scholar
  32. Li, X., & Guskov, I. (2007). 3D object recognition from range images using pyramid matching. In IEEE int’l conf. on computer vision workshop on 3D representation for recognition (pp. 1–6). Google Scholar
  33. Lindeberg, T. (1994). Scale-space theory in computer vision. Dordrecht: Kluwer Academics. Google Scholar
  34. Lindeberg, T. (1998). Feature detection with automatic scale selection. International Journal of Computer Vision, 30, 77–116. Google Scholar
  35. Makadia, A., Patterson, A., & Daniilidis, K. (2006). Fully automatic registration of 3D point clouds. In IEEE int’l conf. on computer vision and pattern recognition, Washington, DC, USA (pp. 1297–1304). Los Alamitos: IEEE Comput. Soc. Google Scholar
  36. Mian, A., Bennamoun, M., & Owens, R. (2004). From unordered range images to 3D models: a fully automatic multiview correspondence algorithm. In Theory and practice of computer graphics, Washington, DC, USA (pp. 162–166). Los Alamitos: IEEE Comput. Soc. CrossRefGoogle Scholar
  37. Mian, A., Bennamoun, M., & Owens, R. (2006). Three-dimensional model-based object recognition and segmentation in cluttered scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(10), 1584–1601. CrossRefGoogle Scholar
  38. Mokhtarian, F., Khalili, N., & Yuen, P. (2001). Curvature computation on free-form 3-D meshes at multiple scales. Computer Vision and Image Understanding, 83, 118–139. MATHCrossRefGoogle Scholar
  39. Morita, S., Kawashima, T., & Aoki, Y. (1992). Hierarchical shape recognition based on 3D multiresolution analysis. In European conf. on computer vision. Google Scholar
  40. Nishino, K., & Ikeuchi, K. (2002). Robust simultaneous registration of multiple range images. In Proc. of fifth Asian conference on computer vision, ACCV 02 (pp. 454–461). Google Scholar
  41. Novatnack, J., & Nishino, K. (2007). Scale-dependent 3D geometric features. In IEEE int’l conf. on computer vision. Google Scholar
  42. Novatnack, J., & Nishino, K. (2008). Scale-dependent/invariant local 3D shape descriptors for fully automatic registration of multiple sets of range images. In European conference on computer vision (pp. 440–453). Google Scholar
  43. Pauly, M., Kobbelt, L. P., & Gross, M. (2006). Point-based multi-scale surface representation. ACM Transactions on Graphics, 25(2), 177–193. CrossRefGoogle Scholar
  44. Ponce, J., & Brady, M. (1985). Toward a surface primal sketch. The International Journal of Robotics Research, 2, 420–425. Google Scholar
  45. Schlattmann, M. (2006). Intrinsic features on surfaces. In Central European seminar on computer graphics (pp. 169–176). Google Scholar
  46. Skelly, L. J., & Sclaroff, S. (2007). Improved feature descriptors for 3-d surface matching. In: Proc. SPIE conf. on two- and three-dimensional methods for inspection and metrology (Vol. 6762, pp. 63–85). Google Scholar
  47. Stein, F., & Medioni, G. (1992). Structural indexing: efficient 3-D object recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 125–145. CrossRefGoogle Scholar
  48. Struwe, M. (1985). On the evolution of harmonic mappings of riemannian surfaces. Commentarii Mathematici Helvetici, 60(1), 558–581. MathSciNetMATHCrossRefGoogle Scholar
  49. Sun, Y., & Abidi, M. (2001). Surface matching by 3D point’s fingerprint. In IEEE int.’l conf. on computer vision (Vol. 2, pp. 263–269). Google Scholar
  50. Taati, B. (2009). Generation and optimization of local shape descriptors for point matching in 3-D surfaces. Ph.D. thesis, Queen’s University, Ontario, Canada. Google Scholar
  51. Taati, B., Bondy, M., Jasiobedzki, P., & Greenspan, M. (2007). Variable dimensional local shape descriptors for object recognition in range data. In IEEE int’l conf. on computer vision workshop on 3D representation for recognition. Los Alamitos: IEEE Comput. Soc. Google Scholar
  52. Tang, B., Sapiro, G., & Caselles, V. (2000). Diffusion of general data on non-flat manifolds via harmonic maps theory: the direction diffusion case. International Journal of Computer Vision, 36(2), 149–161. CrossRefGoogle Scholar
  53. Taubin, G. (1995). A signal processing approach to fair surface design. In ACM SIGGRAPH (pp. 351–358). Google Scholar
  54. Umeyama, S. (1991). Least-squares estimation of transformation parameters between two point patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(4), 376–380. CrossRefGoogle Scholar
  55. Unnikrishnan, R., & Hebert, M. (2008). Multi-scale interest regions from unorganized point clouds. In IEEE int’l conf. on computer vision and pattern recognition: workshop on search in 3D (S3D). Google Scholar
  56. Weickert, J., Ishikawa, S., & Imiya, A. (1999). Linear scale-space has first been proposed in Japan. Journal of Mathematical Imaging and Vision, 10(3), 237–252. MathSciNetMATHCrossRefGoogle Scholar
  57. Witkin, A. (1984). Scale-space filtering: a new approach to multi-scale description. In IEEE int’l conf. on acoustics, speech, and signal processing (pp. 150–153). Google Scholar
  58. Zhang, D., & Hebert, M. (1999). Harmonic maps and their applications in surface matching. In IEEE int’l conf. on computer vision and pattern recognition (Vol. 2). Google Scholar
  59. Zou, G., Hua, J., Lai, Z., Gu, X., & Dong, M. (2009). Intrinsic geometric scale space by shape diffusion. IEEE Transactions on Visualization and Computer Graphics, 15, 1193–1200. CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Prabin Bariya
    • 1
  • John Novatnack
    • 1
  • Gabriel Schwartz
    • 1
  • Ko Nishino
    • 1
  1. 1.Department of Computer ScienceDrexel UniversityPhiladelphiaUSA

Personalised recommendations