Generating view models of monotone polyhedrons for visual identification : presentation of results of the PhD thesis

• Autorzy: Salamonczyk Andrzej , Mokrzycki Wojciech S.

Identyfikatory

DOI

10.22630/MGV.2012.21.1

• Języki publikacji: EN

Abstrakty

EN

Main results the PhD dissertation are presented in which the goals were: to develop appropriate methods and algorithms in order to obtain a complete view representation of the object using the idea of the viewing sphere with the perspective projection, to compare and select the best algorithm for this task, and to show how the viewing models can be matched with objects extracted from range images. It was proved that it is possible to obtain the approximate view representation of a monotone polyhedron using the algorithm with the complexity of O(n²) and that the minimum number of matching view representations of a monotone polyhedron given with the data from range images is O(n²). The methods of generating view representations of monotone polyhedrons are investigated for the purpose of visual recognition systems and some of them are presented. View representations are used in many areas including identification tasks, e.g. as an element of visual channel in automation and robotics. The 3D view representation of objects can be constructed offline and saved in a database for further use in the recognition task.

Słowa kluczowe

EN

view representation; generation of view representation; view models

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2012
• Tom: Vol. 21, No. 1/4
• Strony: 3--17
• Opis fizyczny: Bibliogr. 12 poz., tab., wykr.

Twórcy

autor

Salamonczyk Andrzej

• Faculty of Science, University of Natural Sciences and Humanities, Siedlce, Poland

autor

Mokrzycki Wojciech S.

• Faculty of Mathematics and Natural Sciences, The Cardinal Wyszynski University, Warsaw, Poland

Bibliografia

• [1] J. Koenderink, A. van Doorn. The Internal Representation of Solid Shape with Respect to Vision. Biological Cybernetics, 32(4):211–216, 1979.
• [2] R. Jain, R. Kasturi, B. G. Schunck. Machine Vision. McGraw-Hill, New York, USA, 1995.
• [3] M. Dabkowska, W. S. Mokrzycki. Generowanie widoków 3W obiektów do systemu wizualnej identyfikacji. Prace IPI PAN, number 809, 1996.
• [4] M. Dabkowska, W. S. Mokrzycki: Multi-view models of convex polyhedron. Machine Graphics and Vision, 6(4):419-450, 1997.
• [5] M. Kowalczyk, W. S. Mokrzycki. Obtaining Complete 2.5D View Representation of Polyhedra Using Concept of Seedling Single-View Area. Comput. Vis. Image Underst., 91(3):280–301, 2003.
• [6] M. Frydler, W. S. Mokrzycki. New, Fast Algorithm of 3D Multiview Polyhedron Representation Generation on View Sphere with Perspective. Proc. Advanced Computer Systems CCV(ACV)’04, Prague, May 15-16, 2004.
• [7] M. Kowalczyk, W. Mokrzycki. Concept of 3D View Model of Non-Convex Polyhedra Generation Using View Sphere Partitioning into Single-View Areas. Computer Recognition Systems, Advances in Soft Computing vol. 30, 411–418, 2005.
• [8] W. S. Mokrzycki, A. Salamończyk. New Results in Generation of Accurate 3D Multiview Representation of Monotonous Polyhedrons. Computer Recognition Systems 2, Advances in Soft Computing vol. 45, 100–107, 2007.
• [9] W. S. Mokrzycki, A. Salamończyk. Spiral Scanning of Faces to Obtain Complete 3D View Representation of Monotonous Polyhedra. Computer Recognition Systems 2, Advances in Soft Computing vol. 45, 171–178, 2007.
• [10] A. Salamonczyk, W. Mokrzycki. Generation of View Representation from View Points on Spiral Trajectory. Image Processing and Communications Challenges 2, Advances in Soft Computing vol. 84, 67–74, 2010.
• [11] E. Neuman. Inequalities and Bounds for Generalized Complete Elliptic Integrals. Journal of Mathematical Analysis and Applications, 373(1):203–213, 2011.
• [12] A. Salamonczyk. Generowanie modeli widokowych wielościanów monotonnych do identyfikacji wizualnej. Phd thesis. Institute of Fundamental Technological Research, Polish Academy of Sciences.