PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Self-Correcting Neural Network for Stereo-matching Problem Solving

Wybrane pełne teksty z tego czasopisma
Identyfikatory
Warianty tytułu
Języki publikacji
EN
Abstrakty
EN
In the present paper we describe innovative architecture of artificial neural network based on Hopfield structure - Self Correcting Neural Network (SCNN). It is implementation similar to dual mode Hopfield-like network for solving stereo matching problem. Considered network consists of basic layer of neurons implemented as analogue Hopfield-like network and supervising layer. Thanks to the supervising layer, there is a possibility of modification of the connection weights between the neurons in the basic layer. This enables the improvement of the network performance (accuracy). Authors propose a depth map use for image segmentation and objects auto-selection. High enough accuracy of these processes can be achieved when proposed network (SCNN) is applied. Similar idea can be applied also for images noise removal. In the present article we also describe in detail neurons dynamics in the basic and supervising layers of the SCNN. The network considered here was a subject of experimental tests using real stereo pictures as well as simulated stereo images. This enabled calculation of error and direct comparison with classic analogue Hopfield neural network.
Wydawca
Rocznik
Strony
457--482
Opis fizyczny
Bibliogr. 78 poz., rys.
Twórcy
autor
  • Institute of Computational Intelligence Czestochowa University of Technology Al. A.K. 36, 42-201 Czestochowa, Poland
  • Institute of Computational Intelligence Czestochowa University of Technology Al. A.K. 36, 42-201 Czestochowa, Poland
Bibliografia
  • [1] I. Aleksander: Artificial vision for robots, Korgan Page, 1983.
  • [2] N. Ayache: Artificial vision for mobile robots: stereo vision and multi sensory perception,MIT Press, 1991.
  • [3] J.J. Orteu: 3-D computer vision in experimentalmechanics, Optics and Lasers in Engineering 47 (3-4) (2009) 282-291.
  • [4] Breve F., Zhao L., Quiles M., Macau E.: Chaotic phase synchronization and desynchronization in an oscillator network for object selection, Neural Networks, 22(2009) 728-737.
  • [5] Dunka A., Haffegeea A., Alexandrov V.: Selection methods for interactive creation and management of objects in 3D immersive environments, Procedia Computer Science 1(2010), 2609-2617.
  • [6] Mokhtarian F., Abbasi S.: Robust automatic selection of optimal views in multi-view free-form object recognition, Pattern Recognition 38(2005), 1021 - 1031.
  • [7] L. Alvarez: Dense Disparity Map Estimation Respecting Image Discontinuities: A PDE and Scale-Space Based Approach, Journal of Visual Communication and Image Representation 13(2002) 3-21.
  • [8] O. Faugeras: Three-dimensional computer vision. A geometric viewpoint, MIT, 1993.
  • [9] W. E. L. Grimson: Computational experiments with a feature based stereo algorithm, IEEE Trans. Pattern Anal. Mach. Intell. 7 (1985) 17-34. [See also MIT Memo 762, January 1984.]
  • [10] Y. Ohta, T. Kanade: Stereo by intra- and inter-scanline search, IEEE Trans. Pattern Anal. Mach. Intell. 7(1985) 139-154
  • [11] S. B. Pollard, J. E. W. Mayhew, and J. P. Frisby, PMF: a stereo correspondence algorithm using a disparity gradient constraint, Perception 14(1985) 449-470.
  • [12] N. Ayache and F. Lustman: Fast and reliable passive trinocular stereovision, in Proc. First Int. Conf. on Computer Vision, London, England, June 1987, pp. 422-427, IEEE Comput. Soc. Press, Los Alamitos, CA.
  • [13] J.H. McIntosh and K. M. Mutch: Matching straight lines, Comput. Vision Graphics Image Process, 43(1998) 386-408.
  • [14] G. Medioni and R. Nevatia: Segment based stereo matching, Comput. Vision Graphics Image Process, 31(1985) 2-18.
  • [15] A.T. Brint and M. Brady: Stereo matching of curves, Image Vision Comput. 8(1990) 50-56.
  • [16] N.M. Nasrabadi: A stereo vision technique using curve-segments and relaxation matching, IEEE Trans. Pattern Anal. Mach. Intell. 14(1992) 566-572.
  • [17] L. Robert, O. Faugeras: Curve-based stereo: figural continuity and curvature, in Proc. Int. Conf. on Computer Vision and Pattern Recognition, Lahaina, Hawai, June 3-6, 1991, pp. 57-62, IEEE Comput. Soc. Press, Los Alamitos, CA.
  • [18] M. Bazarganigilani: Optimized Image Feature Selection Using Pairwise Classifiers, JAISCR, 1(2)(2011) 147-153.
  • [19] D.J. Fleet, A.D. Jepson: Computation of component image velocity from local phase information, Internat. J. Comput. Vision 5(1990) 77-104.
  • [20] D. J. Fleet and A. D. Jepson: Stability of phase information, IEEE Trans. Pattern.Anal.Mach. Intell. 15(1993) 1253-1268.
  • [21] M.R.M. Jenkin, A. D. Jepson: Recovering local surface structure through local phase difference methods, CVGIP: Image Understanding 59(1994) 72-93.
  • [22] Z.-G. Hou: A hierarchical optimization neural networkfor large-scale dynamic systems, Automatica 37(2001) 1931-1940.
  • [23] S. Zlotnik, P. Díez: Hierarchical X-FEM for n-phase flow (n¿2), Comput. Methods Appl. Mech. Engrg. 198(2009) 2329-2338.
  • [24] M. Singh, M.F. Hassan: Hierarchical optimisation for non-linear dynamical systems with non-separable cost functions, Automatica, 14(1) (1978) 99-101.
  • [25] R. Deriche, C. Bouvin, O. Faugeras: A level-set approach for stereo, Investigative Image Processing, Boston, MA, Nov. 1996, SPIE Proceedings 2942(1997) pp. 150-161.
  • [26] O. Faugeras and R. Keriven: Variational principles, surface evolution, PDE’s, level set methods and the stereo problem, IEEE Trans. Image Process. 7(1998) 336-344.
  • [27] F. Heitz, P. Perez, and P. Bouthemy: Multiscale minimization of global energy functions in some visual recovery problems, CVGIP: Image Understanding 59(1994) 125-134.
  • [28] L. Robert, R. Deriche: Dense depth map reconstruction: a minimization and regularization approach which preserves discontinuities, in Computer Vision-ECCV 1996 (B. Buxton and R. Cipolla, Eds.) 1, pp. 439-451, Lecture Notes in Computer Science 1064, Springer-Verlag, Berlin, 1996.
  • [29] F. Devernay and O. D. Faugeras: Computing differential properties of 3-D shapes from stereoscopic images without 3-D models, in Proc. IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, June 21-23, 1994, pp. 208-213.
  • [30] K. Nishihara: Practical real-time imaging stereo matcher, Opt. Engineering 23(1984) 536-545.
  • [31] P. Fua: A parallel stereo algorithm that produces dense depth maps and preserves image features, Mach. Vision Appl. 6(1993) 35-49.
  • [32] C. Sun: A fast stereo matching method. Digital Image Computing: Techniques and Applications, Massey University, Auckland, New Zealand, 1997 pp. 95-100.
  • [33] C. Sun: Fast stereo matching using rectangular subregioning and 3D maximum-surface techniques, International Journal of Computer Vision 47(2002) 99-117.
  • [34] C. Sun, R. Jones, H. Talbot, X. Wu, K. Cheong, R. Beare, M. Buckley, M. Berman: Measuring the distance of vegetation from powerlines using stereo vision, ISPRS Journal of Photogrammetry and Remote Sensing 60(2006) 269-283.
  • [35] B. Porr, B. Nurenberg, F. Worgotter: A VLSI-Compatible Computer Vision Algorithm for Stereoscopic Depth Analysis in Real-Time, International Journal of Computer Vision 49(1)(2002), 39-55.
  • [36] V. Kolmogorov: Graph Based Algorithms for Scene Reconstruction from Two or More Views, Cornell University, PhD thessis, 2004.
  • [37] V. Kolmogorov, P.Monasse, P. Tan: Kolmogorov and Zabih’s Graph Cuts StereoMatching Algorithm, Image Processing On Line 4(2014) 220-251.
  • [38] J.J.Hopfield, D.W. Tank: ”Neural” computation of decisions in optimization problems, Biological Cybernetics 52(1985) 141-152.
  • [39] J.J.Hopfield, D.W. Tank: Artificial neural networks, IEEE Circuits and Devices Magazine 8(1988) 3-10.
  • [40] J.J. Hopfield: Computing with neural circuits: a model, Science 233(1986) 625-633.
  • [41] J J.Hopfield, D.W. Tank: Collective computation in neuron-like circuits, Scientific American 11(1987) 62-70.
  • [42] R. Cierniak: A new approach to image reconstruction from projections problem using a recurrent neural network, Applied
  • [43] J. J. Lee, J. C. Shim and Y. H. Ha: Stereo correspondence using the Hopfield neural network of a new energy function, Pattern Recognition 27(1994), 1513-1522.
  • [44] Y. Zhou and R. Chellappa: Artifcial Neural Networks for Computer vision, Springer, New York, 1992.
  • [45] M. S. Mousavi and R. J. Schalkoff: ANN implementation of stereo vision using a multi-layer feedback architecture, IEEE Trans. Systems Man Cybernnet. 24(1994) 1220-1238.
  • [46] G. Pajeras, J. M. Cruz and J. Aranda: Relaxation by Hopfield Network in Stereo Image Matching, Pattern Recognition 31(5)(1998) 561-574.
  • [47] T.H. Sun, M. Chen , S. Lo, F.C. Tien: Face recognition using 2D and disparity eigenface, Expert Systems with Applications 33(2007) 265-273.
  • [48] G. Joya, M.A. Atencia, F. Sandoval: Hopfield neural networks for optimization: study of the different dynamics, Neurocomputing 43(2002) 219-237.
  • [49] C.T. Tsai, J.H.Wang, Y.N. Sun: Livet stereoscopic visualization by using Hopfield neural nets, Neural Computing and Applications 7(3)(1998) 229-237.
  • [50] L. Laskowski, A Novel Continuous Dual Mode Neural Network in Stereo-Matching Process. Lecture Notes in Computer Science 6354(2010) 294-297.
  • [51] L. Laskowski, Objects Auto-selection fromStereo-Images Realized by Self-Correcting Neural Network, Lecture Notes in Computer Science 7267 (2012) 119-125.
  • [52] A.K. Jain: Fundamentals of digital image processing, Prentice-Hall, 1989.
  • [53] R. Hartley, A. Zisserman: Multiple View Geometry in Computer Vision, Cambridge University Press, 2003.
  • [54] Y. Ma, J. Kosecka, S. Soatto, S. Sastry: An Invitation to 3-D Vision – From Images to Models, Springer Science and Business Media, 2004.
  • [55] N. Ayache, C. Hansen: Rectification of Images for Binocular and Trinocular Stereovision, INRIA Technical Report No 860, 1988.
  • [56] H.A. Bouayed, E.E. Pissaloux, S.M. Abdallah: Vision system for fast 3D obstacle detection via stereovision matching, SPIE Int. Conf. on Intelligent Robots and Computer Vision, Boston, 2001.
  • [57] H.B. Barlow, C. Blackmore, J.D.Pettigrew: The natural mechanism of binocular depth discrimination, J. Physiology 193 (1967) 327-342.
  • [58] D. Marr, T.Poggio: Cooperative computation of stereo disparity, Science 194(1976) 283-287.
  • [59] R.B. Fisher: From surfaces to objects: computer vision and three dimensional scene analysis, John Wiley and Sons Ltd, 1989.
  • [60] P. Fua: A parallel stereo algorithm that produces dense depth maps and preserves image features, INRIA Technical Report 1369 (1991).
  • [61] S. Lee, J. Park: Dual-mode dynamics neural network (D2NN) for knapsack packing problem, Neural Networks, IJCNN 3(25-29)(1993) 2425 - 2428.
  • [62] S. Lee, J. Park: Dual-mode dynamics neural networks for combinatorial optimization, Neurocomputing 8(1995) 283-304.
  • [63] S. Lee, PHD thessis: Dual-mode dynamics neural networks for combinatorial optimization, South California University, Los Angeles, Thessis id: AAI0576002, 1994.
  • [64] J. Hopfield: Neurons with graded response have collective computational properties like those of two-state neurons, Proc Natl. Acad. Sci. USA 81 (1984) 3088-3092.
  • [65] M.A. Atencia, G. Joya, F. Sandoval: Dynamical analysis of continuous higher order Hopfield networks for combinatorial optimization, Neural Comput. 17 (8) (2005) 1802-1819.
  • [66] S. Abe: Global convergence and suppression of spurious states of the Hopfield neural networks, IEEE Transactions on Circuits and Systems 40(4)(1993) 246-257.
  • [67] N.Bagherzadeh, T. Kerola, B. Leddy, R. Brice: On parallel execution of the traveling salesman problem on a neural network model, Proceedings of the IEEE International Conference on Neural Networks, San Diego, USA 1987, vol.3 pp. 317-324.
  • [68] M. Atencia, H. Boumeridja, G. Joya, F. Garcia-Lagos, F. Sandoval: FPGA implementation of a systems identification module based upon Hopfield networks, Neurocomputing 70 (2007) 2828-2835.
  • [69] R. Cierniak: New neural network algorithm for image reconstruction from fan-beam projections, Neurocomputing 72(2009) 3238-3244.
  • [70] D.J. Amit, H. Gutfreung, H. Sampolinsky: Spin-glass models of neural networks, Physical Review A2 32(2)(1985) 1007-1018.
  • [71] D.J. Amit, H. Gutfreung, H. Sampolinsky: Storing infinite numbers of patterns in a spinglass model of neural networks, Physical Review Letters 55(1985) 1530-1533.
  • [72] J.J. Hopfield: Neural networks and physical systems with emergent collective computational abilities, Proc. of the National Academy of Science of the USA 79(1982) 2554-2558.
  • [73] Y.Wang,W. Lu: Multicriterion image reconstruction and implementation, Computer Vision, Graphics, Image Processing 46(2)(1989) 131-135.
  • [74] Y.Wang,W. Lu: Multiobjective decision making approach to image reconstruction from projections, Journal of the Optical Society of America A - Optical Image Society 8(10)(1991) 1649-1659.
  • [75] B. Kamgar-Parsi: On problem solving with Hopfield neural networks, Biological Cybernetics 62(5)(1990) 415-423.
  • [76] D. Kunz: Suboptimal solutions obtained by the Hopfield-Tank neural network algorithm, Biological Cybernetics 65(1991) 129-133.
  • [77] G.V. Wilson, G.S. Pawley: On the stability of the travelling salesman problem algorithm of Hopfield and Tank, Biological Cybernetics 57(1980) 63-70.
  • [78] K. Lapa,M. Zalasi´nski, K. Cpałka: A NewMethod for Designing and Complexity Reduction of Neuro-fuzzy Systems for Nonlinear Modelling, Lecture Notes in Computer Science 7894(2013), 329-344.
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-48f45036-3b4a-40e9-b462-824db75102ca
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.