Abstract
This paper presents a novel solution to the reconstruction of 3D geometry models from partial, segmented (2.5D or 3D) range views. First, the geometric fusion works entirely on sparse symbolic information, i.e. attributed surface graphs, rather than point data or triangulated meshes. Thus, new sensor data can always be integrated with an existing partial model available for symbolic action planning. Second, assumptions on automatic registration are weaker than those found in related work: the views need not be approximately calibrated, and no pre-existing knowledge of their overlap is needed. In order to find corresponding (redundant) surface features reliably even under high-noise and occlusion conditions we develop Neuro-Fuzzy similarity measures on surface descriptions. Third, we propose a reasonably complete prototype system including algorithms for merging sparse, reduced surface attributes, in particular boundaries. The experimental results from segmented range images of an indoor camera motion sequence demonstrate the ability to cope with unknown camera positions, low image resolution, large measurement and segmentation errors.
Similar content being viewed by others
References
Al-Hamadi, H. and Tsui, H.-T.: 3D surface approximation using polygons of fixed orientation for a vision system in a mobile robot, in: Proc. 4th Intl. Conf. on Signal Processing Applications and Technology, Santa Clara, USA, 28 Sept.-1 Oct. 1993, pp. 1332-1336.
Ashbrook, A. P., Fisher, R. B., Robertson, C. and Werghi, N.: Finding surface correspondences for object recognition and registration using pairwise geometric histograms, in: Proc. 5th Eur. Conf. on Computer Vision, Vol. II, Freiburg, Germany, June 1998, pp. 674-680.
Azarm, K., Bott, W., Freyberger, F., Glüer, D., Horn, J. and Schmidt, G.: Autonomiebausteine des mobilen Roboters MACROBE (in German), in: 9 Fachgespräch Autonome Mobile Systeme, Munich, 28-29 Oct. 1993, pp. 81-94.
Bailey, A. D. and Fröhlich, C.: Reverse engineering a process plant to produce a 3-D CAD model, in: Numerisation 3D '99, The 4th Industrial Congress on 3D Digitizing and Industrial Creation, Paris, France, 19-20 May 1999.
Begevin, R., Soucy, M., Gagnon, H. and Laurendeau, D.: Towards a general multi-view registration technique, IEEE PAMI 18(5) (1996), 540-547.
Berztiss, A. T.: Data Structures: Theory and Practice, Academic Press, New York, 1975.
Besl, P. J.: Surfaces in Range Image Understanding, Springer Series in Perception Engineering, ed. R. C. Jain, Springer, New York, 1988.
Besl, P. J. and McKay, D. N.: A method for registration of 3-D shapes, IEEE Trans. PAMI 14(2) (1992), 239-256.
Blais, G. and Levine, M. D.: Registering multiview range data to create 3D computer objects, IEEE PAMI 17(8) (1995), 820-824.
Boulanger, P. and Blais, F.: Range image segmentation, free space determination, and position estimate for a mobile vehicle, SPIE, Vol. 1831, Mobile Robots VII, 1992, 444-455.
Boyer, E. and Berger, M.-O.: 3D surface reconstruction using occluding contours, Int. J. Computer Vision 22(3) (1997), 219-233.
Bunke, H. and Shearer, K.: A graph distance metric based on the maximal common subgraph, Pattern Recognition Lett. 19 (1998), 255-259.
Bunke, H.: On a relation betweeen graph edit distance and maximum common subgraph, Pattern Recognition Lett. 18 (1997), 689-694.
Burgard, W., Fox, D., Hennig, D. and Schmidt, T.: Estimating the absolute position of a mobile robot using position probability grids, in: Proc. 14th National Conference on Artificial Intelligence.
Dario, P., Rucci, M., Guadagnini, C. and Laschi, C.: An experimental robot system for investigating disassembly problems, in: Proc. IEEE/Tsukuba Intl. Workshop on Advanced Robotics, Tsukuba, Japan, 8-9 Nov. 1993.
Dorai, C., Wang, G., Jain, A. K. and Mercer, C.: Registration and integration of multiple object views for 3D model construction, IEEE Trans. PAMI 20(1) (1998), 83-89.
Dori, D. and Weiss, M.: A scheme for 3D object reconstruction from dimensioned orthographic views, Eng. Appl. of Artificial Intelligence 9(1) (1996), 53-64.
Driankov, Hellendoorn, H. and Reinfrank, M.: An Introduction to Fuzzy Control, 2nd edn, Springer, 1996.
Eggert, D. W., Fitzgibbon, A. W. and Fisher, R. B.: Simultaneous registration of multiple range views for use in reverse engineering of CAD models, Computer Vision and Image Understanding 69(3) (1998), 253-272.
Fan, T. J.: Describing and Recognizing 3-D Objects Using Surface Properties, Springer, New York, 1990.
Faugeras, O. D. and Hebert, M.: The representation, recognition, and locating of 3-D objects, Intl. J. Robotics Research 5(3) (1986), 27-52.
Fischer, D., Kohlhepp, P. and Bulling, F.: An evolutionary algorithm for the registration of 3-D surface representations, Pattern Recognition (Special Issue on Image Registration) 12 (1998), 53-69.
Fisher, R. B., Fitzgibbon, A.W. and Eggert, D.: Extracting surface patches from complete range descriptions, in: Proc. Int. Conf. on Recent Advances in 3-D Digital Imaging and Modeling, Ottawa, Canada, May 1997, pp. 148-155.
Fitzgibbon, A. W., Eggert, D. W. and Fisher, R. B.: High-level CAD model acquisition from range images, Computer-Aided Design 29(4) (1997), 321-330.
Flynn, P. J. and Jain, A. C.: 3D object recognition using invariant feature indexing of interpretation tables, CVGIP: Image Understanding 55(2) (1992), 119-129.
Grimson, W. E. L. and Lozano-Perez, T.: Localizing overlapping parts by searching the interpretation tree, IEEE PAMI 9(4) (1987).
Hebert, M., Ikeuchi, K. and Delingette, H.: A spherical representation for recognition of freeform surfaces, IEEE Trans. PAMI 17(7) (1995), 681-690.
Hilton, A., Stoddart, A. J., Illingworth, J. and Windeatt, T.: Reliable Surface Reconstruction from Multiple Range Images, Lecture Notes in Comput. Sci. 1064, Springer-Verlag, 1996, 117-126.
Holliday, M., Dougan, A., Gavel, D., Gustaveson, D., Johnson, R., Kettering, B. and Wilhelmsen, K.: Demonstration of automated robotic workcell for hazardous waste characterization, in: IEEE Intl. Conf. on Robotics and Automation, Atlanta, USA, 2-6 May 1993, pp. 788-794.
Hoover, A., Goldgof, D. and Bowyer, K. W.: Extracting a valid boundary representation from a segmented range image, IEEE PAMI 17(9) (1995), 920-924.
Hoover, A., Jean-Baptiste, G., Jiang, X., Flynn, P. J., Bunke, H., Goldgof, D. B., Bowyer, K., Eggert, D. W., Fitzgibbon, A. and Fisher, R. B.: An experimental comparison of range image segmentation algorithms, IEEE PAMI 18(7) (1996), 673-689.
Hoppe, H., DeRose, T., Duchamp, T., McDonald, J. and Stuetzle, W.: Surface reconstruction from unorganized points, Computer Graphics 26 (1992), 71-78.
Integrated Vision Products (IVP), RS2200 RANGER PCI, User Documentation, Linköping, Sweden, 1996.
Jiang, X. and Bunke, H.: Three-dimensional Computer Vision (in German), Springer, 1997.
Johnson, A. E. and Hebert, M.: Surface registration by matching oriented points, in: International Conference on Recent Advances in 3-D Digital Imaging and Modeling, Ottawa, Ontario, 12-15 May 1997.
Kak, A. and Edwards, J. L.: Experimental state of the art in 3D object recognition and localization using range data, in: Proceedings of Workshop on Vision for Robots, IEEE Press, Pittsburgh, PA, 1995.
Kohlhepp, P.: Combining region and edge based segmentation for robust 3D localization in range mages, in: 2nd Asian Conference on Computer Vision (ACCV), Singapore, 2-3 Dec. 1995, pp. 254-258.
Kohlhepp, P., Fischer, D. and Hoffmann, E.: Intrinsic line features and contour metric for locating 3-D objects in sparse, segmented range images, Image and Vision Computing (Special Issue on Visual Form Analysis) 17 (1999), 403-417.
Kosko, B.: Neural Networks and Fuzzy Systems, Prentice-Hall, 1992.
Kuntze, H.-B., Schmidt, D., Haffner, H. and Loh, M.: KARO-a flexible robot for smart sensorbased sewer inspection, in: NODIG '95, Dresden, 19-22 Sept. 1995, pp. 367-374.
Lang, S. Y. T. andWong, A. K. C.:Map making for an autonomous mobile robot, in: 2nd IARP Workshop on Sensor Fusion and Environmental Modeling, Oxford, UK, Sept. 1991.
Lin, C.-C. and Tummala, R. L.: Mobile robot navigation using artificial landmarks, J. Robotics Systems 14(2) (1997), 93-106.
Mohr, R., Quan, L. and Veillon, F.: Relative 3D reconstruction using multiple uncalibrated images, The Internat. J. Robotics Research 14(6) (1995), 619-632.
NN, fuzzyTech 4.1 reference manual, Inform GmbH (Gemany), 1996.
Orr, M. J. L., Hallam, J. and Fisher, R. B.: Fusion through interpretation, in: G. Sandini (ed.), Proc. 2nd European Conf. on Computer Vision, St. Margherita Ligure, Italy, 1992, pp. 801-805.
Shaffer, G. K., Stentz, A., Whittaker, W. L. and Fitzpatrick, K. W.: Position estimator for underground mine equipment, in: Proc. Intl. Workshop on Information Processing in Autonomous Mobile Robots, Munich, 6-8 Mar. 1991, pp. 1-10.
Shapiro, L. G. and Haralick, R. M.: Organization of relational models for scene analysis, IEEE PAMI 4(11) (1982), 595-602.
Soucy, M. and Laurendeau, D.: A general surface approach to the integration of a set of range views, IEEE PAMI 17(4) (1995), 344-358.
Talluri, R. and Aggarwal, J. K.: Mobile robot self-location using constrained search, in: IEEE/RSJ Intl. Workshop on Intelligent Robots and Systems IROS '91, Osaka, Japan, 3-5 Nov. 1991, pp. 903-908.
Thrun, S., Gutmann, J.-S., Fox, D., Burgard, W. and Kuipers, B.: Integrating topological and metric maps for mobile robot navigation: A statistical approach, in: Proceedings of the 15th National Conference on Artificial Intelligence (AAAI-98), July 1998.
Thrun, S. and Brücken, A.: Integrating grid-based and topological maps for mobile robot navigation, in: Proc. of the 13th National Conference on Artificial Intelligence AAAI, Portland, Oregon, Aug. 1996.
Várady, T., Martin, R. and Cox, J.: Reverse engineering of geometric models-an introduction, Computer Aided Design 29(4) (1997), 255-268.
Wallner, F., Graf, R. and Dillmann, R.: Real-time map refinement by fusing sonar and active stereo-vision, in: IEEE International Conference on Robotics and Automation, Nagoya, 1995.
Wilkes, D.: Using point range samples for reprojection of model views for landmark-based robot navigation, SPIE, Vol. 2355, Sensor Fusion VII, 1994, 147-156.
Xie, S. and Calvert, T. W.: Incremental construction of 3-D models from a sequence of framed views, in: Proc. Graphics Interface '86, Vancouver, 1986, pp. 300-306.
Yamauchi, B. and Langley, P.: Place recognition in dynamic environments, J. Robotics Systems 14(2) (1997), 107-120.
Yan, Q.-W., Chen, P. and Tang, Z.: Efficient algorithm for the reconstruction of 3D objects from orthographic projections, Computer Aided Design 26(9) (1994), 699-717.
http://www.iai.fzk.de/Sombrero/somb_objerk/similarity/NF_tool.html: Neuro-Fuzzy rule base.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fischer, D., Kohlhepp, P. 3D Geometry Reconstruction from Multiple Segmented Surface Descriptions Using Neuro-Fuzzy Similarity Measures. Journal of Intelligent and Robotic Systems 29, 389–431 (2000). https://doi.org/10.1023/A:1008164101786
Issue Date:
DOI: https://doi.org/10.1023/A:1008164101786