Automatic surface registration in computer vision systems

A. A. Krylovetsky ; I. S. Chernikov ; S. D. Kurgalin

Matematičeskoe modelirovanie, Tome 25 (2013) no. 3, pp. 33-46.

Résumé

Registration of range data (surfaces obtained by scene object scanning) is a fundamental problem of three-dimensional computer vision. Efficiency of computer vision system mainly rely on successful decision of this issue. The principle of registration procedure is automatic detection of surfaces parts which correspond to the same area of the scene. The most successful approach to this problem is based on local surface descriptors. In the paper 3D spin images and oriented spin images are proposed and its higher efficiency in comparison with found to be traditional simple spin images is shown.

Détail

Mots-clés : registration
Keywords: spin images, local surface descriptors, computer vision.

Bibliographie

[1] The Digital Michelangelo Project http://www.graphics.stanford.edu/projects/mich/

[2] Levoy M., Pulli K., Curless B., Rusinkiewicz S., Koller D., Pereira L., Ginzton M., Anderson S., Davis J., Ginsberg J., Shade J., Fulk D., “The Digital Michelangelo Project: 3D scanning of large statues”, SIGGRAPH 2000, Computer Graphics Proceedings (July 24–28, 2000), Annual Conference Series, Addison-Wesley, 131–144

[3] Callieri M., Fasano A., Impoco G., Cignoni P., Scopigno R., Parrini G., Biagini G., “Roboscan: An automatic system for accurate and unattended 3d scanning”, 3DPVT'04, Second Int. Symp. on 3D Data Processing, Visualization and Transmission (Sept. 6–9, 2004), IEEE Comp. Soc. (to appear)

[4] Polhemus. The FastSCAN Cobra scanning system, 2003 http://www.polhemus.com/fastscan.htm

[5] Steinbichler Optotechnik. COMET series, 2004 http://www.steinbichler.de/

[6] Gianfranco D. L. L., Guido M. C., “A frequency domain technique for range data registration”, IEEE Trans. on Pattern Analysis and Machine Intelligence, 24:11 (2002), 1468–1484 | DOI

[7] Delingette H., Hebert M., Ikeuchi K., “Shape representation and image segmentation using deformable surfaces”, Image and vision computing, 10 (1992), 132–144 | DOI

[8] Delingette H., Hebert M., Ikeuchi K., “A spherical representation for the recognition of curved objects”, Proc. IEEE Int. Conf. On Computer Vision (1993), 103–112

[9] Vranic D., Saupe D., “3D model retrieval with spherical harmonics and moments”, Proc. of the DAGM (2001), 392–397 | Zbl

[10] Funkhouser T., Kazhdan M., Rusinkiewicz S., “Rotation invariant spherical harmonic representation of 3d shape descriptors”, Eurographics Symposium on Geometry Processing (2003), 156–164

[11] Vanden Wyngaerd J., Van Gool L., “Automatic crude patch registration: Toward automatic 3d model building”, Computer Vision and Image Understanding, 86:2 (2002), 8–26 | DOI

[12] Schön N., Häusler G., “Automatic coarse registration of 3D surfaces”, Vision, modeling, and visualization, 2005, 71–178

[13] Stein F., Medioni G., “Structural indexing: Efficient 3-d object recognition”, IEEE Trans. Pattern Anal. Mach. Intell., 14 (1992), 125–145 | DOI

[14] Chua C. S., Jarvis R., “Point signatures: A new representation for 3d object recognition”, Int. J. Comput. Vision, 25 (1997), 63–85 | DOI

[15] Sun Y., Paik J., Koschan A., Page D. L., Abidi M. A., “Point fingerprint: A new 3-d object representation scheme”, IEEE Transactions on Systems, Man and Cybernetics, 3:4, 3 August (2003), 712–717

[16] Frome A., Huber D., Kolluri R., Bulow T., Malik J., “Recognizing Objects in Range Data Using Regional Point Descriptors”, ECCV, Proceedings of the European Conference on Computer Vision (May, 2004)

[17] Johnson A. E., Hebert M., IEEE Trans. Pattern Analysis and Machine Intelligence, 21:5 (1999), 433–449 | DOI

[18] Roth G., “Registering two overlapping range images”, 3DIM'99, Second Int. Conf. on 3D Digital Imaging and Modelling (October 1999), 191–200

[19] Besl P. J., McKay N. D., “A method for registration of 3-D shapes”, IEEE Transactions on Pattern Analysis and machine Intelligence, 14:2, February (1992), 239–258 | DOI

[20] Chen Y., Medioni G., “Object modelling by registration of multiple range images”, International Journal of Image and Vision Computing, 10:3, April (1992), 145–155 | DOI

[21] Turk G., Levoy M., “Zippered Polygon Meshes from Range Images”, Proc. SIGGRAPH (1994)

[22] Masuda T., Sakaue K., Yokoya N., “Registration and Integration of Multiple Range Images for 3-D Model Construction”, Proc. CVPR (1996)

[23] Friedman J., Bentley J., Finkel R., “An algorithm for finding best matches in logarithmic expected time”, ACM Trans. On Math. Software, 1977

[24] Simon D., Fast and Accurate Shape-Based Registration, Ph. D. Dissertation, Carnegie Mellon University, 1996 | Zbl

[25] Clarkson K., “A randomized algorithm for closest point queries”, SIAM J. Computing, 17 (1998), 830–847 | DOI | MR

[26] Benjemaa R., Schmitt F., “Fast Global Registration of 3D Sampled Surfaces Using a Multi-Z-Buffer Technique”, Proc. 3DIM (1997)

[27] Rusinkiewicz S., Levoy M., “Efficient Variants of the ICP Algorithm”, Third International Conference on 3D Digital Imaging and Modeling (2001)

[28] Pottmann H., Leopoldseder S., Hofer M., “Registration without ICP”, Geometric Modeling and Industrial Geometry Group, Vienna Univ. of Technology, 2004

[29] Endres F., Plagemann C., Stachniss C., Burgard W., “Unsupervised discovery of object classes from range data using latent Dirichlet allocation”, Robotics: Science and Systems V (Seattle, USA, June 2009)