Abstract
We are building a system that can rapidly determine the pose of a known object in an unknown view using a view class model of the object. The system inputs a three-dimensional CAD model; converts it to a three-dimensional vision model that contains the surfaces, edges, vertices, and topology of the object; and uses the vision model to determine the view classes or representative views of the object. In this paper we define therelational pyramid structure for describing the features in a particular view or view class of an object and thesummary structure that is used to summarize the relational information in the relational pyramid. We then describe an accumulator-based method for rapidly determining the view class(es) that best match an unknown view of an object.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Andress KM, Kak AC (1988) Evidence accumulation and flow of control in a hierarchical spatial reasoning system. Al Magazine Summer, 75–94
Bolles RC, Cain RA (1982) Recognising and locating partially visible objects: The local-feature focus method. International Journal of Robotics Research 1(3):57–82
Boyer KL, Kak AC (1988) Structural stereopsis for 3D vision. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-10(2): 144–166
Brooks RA (1981) Symbolic reasoning among 3D models and 2D images. Artificial Intelligence 17(1–3):285–348
Camps OI, Shapiro LG, Haralick RM (1989) PREMIO: The use of prediction in a CAD-model-based vision system. Technical Report #EE-ISL-89-01, Department of Electrical Engineering, University of Washington, July
Chakravarty I(1979) A generalized line and junction labelling scheme with application to scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-l(2):202–205
Chakravarty I, Freeman H (1982) Characteristic views as a basis for three-dimensional object recognition. In: Proceedings of SPIE 336(Robot Vision), pp 37–45
Chu NT, Shapiro LG (1990) Experiments in model-based using a relational pyramid representation. In: Proceedings of the SPIE Conference on Applications of Artificial Intelligence VIII, pp 236–240
Garvey TD, Lowrance JD, Fischler MA (1981) An intelligent technique for integrating knowledge from disparate sources. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp 319–325
Gigus Z, Canny J, Seidel R (1988) Efficiently computing the aspect graphs of polyhedral objects. In: Proceedings of the 2nd International Conference on Computer Vision, pp 30–39
Hanson C, Henderson T (1988) Toward the automatic generation of recognition strategies. In: Proceedings of the 2nd International Conference on Computer Vision. Tampa, FL, pp 275–279
Henderson T, Hansen C, Samal A, Ho CC, Bhanu B (1986) CAGD-based 3-D visual recognition. In: Proceedings of the Eight International Conference on Pattern Recognition. Paris, October, pp 230–232
Ikeuchi K (1987) Generating an interpretation tree from a CAD model for 3D-object recognition in bin-picking tasks. International Journal of Computer Vision 1(2): 145–165
Kak AC, Vayda AJ, Cromwell RL, Kim WY, Chen CH (1988) Knowledge-based robotics. International Journal of Production Research 26(5):707–734
Lee SJ, Haralick RM, Shapiro LG (1987) Morphological edge detection. IEEE Journal of Robotics and Automation RA-3(2) April, 142–156
Lounsbery JM (1989) The renaissance modeling systems: A tutorial. Technical Report 89-01-05, Department of Computer Science and Engineering, University of Washington, Seattle, WA, January
Narasimhamurthi N, Jain R (1988) CAD-based object recognition: Incorporating metric and topological information. In: Proceedings of the SPIE Conference on Digital and Optical Shape Recognition and Pattern Recognition, vol. 938, April, pp 436–443
Plantinga H, Dyer C (1986) An algorithm for constructing the aspect graph. 27th Annual Symposium on Foundations of Computer Science 123–131
Ponce J, Chelberg D (1987) Finding the limbs and cusps of generalized cylinders. International Journal of Computer Vision 1(3): 195–210
Rosenfeld A, Hummel RA, Zucker SW (1976) Scene labeling by relaxation operators. IEEE Transactions on Systems, Man, and Cybernetics SMC-6:420–433
Sanfeliu A, Fu KS (1983) A distance measure between attributed relational graphs for pattern recognition. IEEE Transactions on Systems, Man, and Cybernetics SMC-13, pp 353–362
Shapiro LG (1978) Inexact matching in a syntactic pattern recognition system. Pattern Recognition 10:313–321
Shapiro LG (1980) A structural model of shape. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-2(2):111–126
Shapiro LG, Haralick RM (1981) Structural descriptions and inexact matching. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-3(5):504–519
Shapiro LG, Haralick RM (1985) A metric for comparing relational descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-7(1):90–94
Stewman J, Bowyer KW (1988) Creating the perspective projection aspect graph of polyhedral objects. In: Proceedings of the 2nd International Conference on Computer Vision, pp 494–500
Thornton KB, Shapiro LG (1989) Image matching for view class construction. In: Proceedings of the 6th Israeli Conference on Artificial Intelligence, Vision, and Pattern Recognition, pp 220–229
Wong AKC, You M (1985) Entropy and distance of random graphs with application to structural pattern recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-7(5):599–609
Author information
Authors and Affiliations
Additional information
This research was partially supported by the National Aeronatics and Space Administration (NASA) through a subcontract from Machine Vision International.
Rights and permissions
About this article
Cite this article
Shapiro, L.G., Lu, H. Accumulator-based inexact matching using relational summaries. Machine Vis. Apps. 3, 143–158 (1990). https://doi.org/10.1007/BF01214427
Issue Date:
DOI: https://doi.org/10.1007/BF01214427