3W modele widokowe niewypukłych wielościanów na sferze widokowej z perspektywą

• Autorzy: Mokrzycki W. S.

Warianty tytułu

EN

3D view models of nonconvex polyhedra on view sphere with perspective

• Języki publikacji: PL

Abstrakty

PL

Opracowanie dotyczy generowania 3W widokowych modeli (zwanych w literaturze modelami 2 ? W) niewypukłych wielościanów wg koncepcji sfery widokowej z rzutowaniem perspektywicznym, będących kompletną reprezentacją tego wielościanu. Modele są przewidziane do systemów identyfikacji wizualnej opartej o nie i mapy głębi sceny. W szczególności, jest opisana nowa koncepcja oraz podany jest algorytm ściano-zależnego generowania widoków wielościanowych i nie wymaga wykonywania dodatkowych czynności ani wprowadzania pomocniczych mechanizmów (np. w postaci tzw. obszarów 1-widokowych) i związanych z nimi długotrwałych obliczeń, jak to występuje w literaturowych metodach.

EN

The elaboration concerns the generation of the $3D$ view models (known in literature as $2\frac{1}{2}D$) nonconvex polyhedron using the concept of the view sphere with perspective projection and forms the complet representation of the polyhedron. The models are destined for visual identification system based on the models and object deep map. In peculiarity, the new concept and algorithm of face-dependent generation of the polyherdon views, which do not need any additional acting or mechanizms (e.g. single-view areas), and time-consuming calculations, are described.

Słowa kluczowe

PL

wizualna identyfikacja obiektów; widokowe 3W dokładne modele wielościanów; sfera widokowa z perspektywą; punkty widokowe

EN

visual object identification; depth map; 3D exact view models; view sphere with perspective; view poin; completness of view model representation

• Wydawca: Instytut Podstaw Informatyki PAN
• Czasopismo: Prace Instytutu Podstaw Informatyki Polskiej Akademii Nauk
• Rocznik: 2003
• Tom: Nr 962
• Strony: 1--11
• Opis fizyczny: Bibliogr. 43 poz., rys.

Twórcy

autor

Mokrzycki W. S.

• Instytut Podstaw Informatyki PAN, ul. Ordona 21, 01-237 Warszawa,

Bibliografia

• 1987
• [1] Connell J.H., Brady M.: Generating and generalizing models of visual objects. AI, 31, 159-183.
• 1989
• [2] Chen C.H., Kak A.C.: A robot vision system for recognizing 3D objects in low-order polynomial time. IEEE Trans. SMC, 19(6), 1535-1563.
• [3] Hansen C., Henderson T.C.: CAGD-based computer vision. IEEE Trans. PAMI. 11(11), 1181-1193.
• 1990
• [4] Bowyer K.W., Dyer Ch.R.: Aspect Graphs: An Introduction and Survey of Recent Results. SPIE, 1395.
• [5] Sallam M., Bowyer K.: Generalizing the aspect graph concept to inclide articulated assemblies. SPIE, 1395, 1150-1156.
• [6] Wong A.K.C., Lu S.W., Rioux M.: Recognition and shape synthesis of 3D objects based on attributed hypergiaphs. IEEE Trans. PAMI 11(3), 279-290.
• 1991
• [7] Gigus Z-. Canny J.. Seidel R.: Efficiently computing and representing aspect graph of polyhedral object. IEEE Trans. PAMI, 13(6), 542-551.
• [8] Flynn P.J.. Jain A.K. CAD-based computer vision: from CAD models to relational graphs. IEEE Trans. PAMI, 13(2), 114-132.
• 1992
• [9] Ponce J., Petitiean S., Kriegnian D.J.: Computing exact aspect graphs of curved objects. Proc ECCV’92, Santa Margarita Ligure, Italy, LNCS 588, 599-614.
• 1993
• [10] Zhank S., Sullivan G.D., Baker K.D.: The automatic construction of a view-independent relational model for 3D object recognition. IEEE Trans. PAMI, 15(6). 531-544.
• 1994
• [11] Camps O.I.: Towards a robust physic-based object recognition system. Object Representation in Computer Vision Proc. Int NSF-ARPA Workshop, NY. Dec., 297-311.
• [12] Petitjean S.: Algebraic geometry and object representation in computer vision. Object Representation in Computer Vision. Proc. Int. NSF-ARPA Workshop, NY, Dec., 155- 165.
• [13] Taubin G.: Discrete surface signal processing: the polygon as the surface element. Proc. Int. NSF-ARPA Workshop, NY, Dec., 167-175.
• 1995
• [14] Bayro-Corrochano E., Sommer G.: Object modelling and collision avoidance using Clifford algebra. Proc. CAIP’95, LNCS 970, Springer-Verlag, Berlin, 699-704.
• [15] Cole P.A.R, Khan M.S.: Modelling 3D rigid objects using the view signature II representation scheme. Proc. CAIP’95, LNCS 970, 154-161.
• [16] Costa M.S., Shapiro L.G.: Analysis of scenes containing multiple non-polyhedral 3D objects. Proc.8th Int. Conf. ICIAP’95, San Remo, Sept., 273-280.
• [17] Leonardis A., Kovacic S., Pernus F.: Recognition and pose determination of 3D objects using multiple views. Proc. CAIP’95, LNCS 970, Springer-verlag, Berlin, 778-783.
• [18] Munkelt O.: Aspect trees: generation and interpretation. Computer Vision and Image Understanding. 61(3), 365-386.
• [19] Shashua A.: Multiple-viev geometry and photometry. Proc. 2nd Asian Conf. on CV ACCV’95, Singapore, Dec., 395-404.
• [20] Suk T., Flusser J.: The projective invariants for polygon. Proc. CAIP’95, LNCS 970, Springer-Verlag, 729-734.
• [21] Zisserman A., Mundy J., Forsyth D., Liu J., Pillow N.. Rothwell C., Utcke S.: Class-based grouping in perspective images. http://www.robots.ox.ac.uk/~vgg , 1-6.
• 1996
• [22] Arbel T., Ferrie F.P.: Informative vievs and seguential recognition. Proc. ECCV’96, Cambridge, UK, April, 469-481.
• [23] Ayoung-Chee N., Dudek G., Ferrie F.P.: A hybrid approach to 3D representation. Proc. Int. Workshop ECCV’96, Cambridge, UK, April, 321-333.
• [24] Hlavac V., Leonardis A., Werner T.: Automatic selection of reference views for image-based scene representation. Proc. ECCV’96, Cambridge, UK, April, 526-535.
• [25] Rothwell C., Mundy J., Hoffman B.: Representing objects using topology. Proc. Int. Workshop ECCV’96. Cambridge, UK, April, 79-108.
• [26] Tarabanis K., Tsai R.Y., Kaul A.: Computing occlusion-free viewpoints. IEEE Trans. PAMI, 18(3). 279-292.
• 1997
• [27] Arbel T., Ferrie F.P.: Informative views ans seguential recogntion. Proc. ECCV’96, Cambridge, UK, April, 469-481.
• [28] Dąbkowska M., Mokrzycki W.S.: Multiview models of convex polyhedra. MG&V, 6(4), 419-450.
• [29] Dorai C., Jain A.K.: COSMOS - a representation scheme for 3D free-form objects. IEEE Trans. PAMI, 19(10), 1115-1130.
• [30] Dorai C., Jain A.K.: Shape spectrum based view grouping and matching of 3D free-form objects. IEEE Trans. PAMI, 19(10), 1139-1146.
• [31] Dorai C., Weng J., Jain A.K.: Optimal registration of object views using range data. IEEE Trans. PAMI, 19(10), 1131-1138.
• [32] Madsen C.B., Christensen H.I.: A viewpoint planning strategy for determining true angles on polyhedral objects by camera alignment. IEEE Trans. PAMI, 19(2), 158-163.
• [33] Malik R., Whangbo T.: Angle densities and recognition of 3D objects. IEEE Trans. PAMI, 19(1), 52-57.
• [34] Shimshoni I., Ponce J.: Finite-resolution aspect graphs of polyhedral objects.
• 1998
• [35] Dąbkowska M., Mokrzycki W.S.: A new view model of convex polvhedra with featuredependent viev. MG&V, 7(1/2), (Proc. GKPO’98, Borki, Poland, 18-22 May), 325-334.
• [36] Dąbkowska M., Mokrzycki W.S.: Comparison of two chosen methods of feature dependent vievs generation. Proc. UKROBRAZ’98, Kijev, 19-23 Oct..
• [37] Dąbkowska M., Mokrzycki W.S.: Conditions on models for object visual identification. Proc. ACS’98, Szczecin, 19-20 Nov.,
• [38] Elnagar A., Basu A.: From 2D surface patches to 3D reconstructed models: theory and applications. PR, 31(10), 1419-1432.
• [39] Fitzgibbon A.W., Cross G., Zisserman A.: Automatic 3D model construction for turn-table sequences, http://www.robots.ox.ac.uk/~vgg , 1-16.
• [40] Kovacic S., Leonardis A.: Planning sequences of views for 3D object recognition and pose determination. PR, 31(10), 1407- 1417.
• 1999
• [41] Kowalczyk M., Mokrzycki W.S.: Determining complete object’s view model by joining one-view areas. Proc. ACS’99, Szczecin, 18-19 Nov., 68-72.
• 2001
• [42] Kowalczyk M., Mokrzycki W.S.: Obtaining complete 2 ¡¡D view representation of polyhedra using concept of seedling single-view area. Submited to CVk.lU.
• 2002
• [43] Kowalczyk M., Mokrzycki W.S.: A new method of finding one-view areas and tight view sphere covering. Proc. ICCVG’02, Zakopane, Poland, Sept. 25-29, 443-449.