Dictionary learning for stereo image representation

IEEE Transactions on Image Processing

Volumn 20, Issue 4, 2011, Pages 921-934

  Tošić, Ivana ^a   Frossard, Pascal ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b EPFL   (Switzerland)

Author keywords

Dictionary learning; multi view imaging; omni directional cameras; sparse approximations

Indexed keywords

CAMERA POSE ESTIMATION; DICTIONARY LEARNING; EXPECTATION-MAXIMIZATION ALGORITHMS; FEATURE MATCHING; GEOMETRIC STRUCTURE; GEOMETRIC TRANSFORM; INTRINSIC GEOMETRY; MAXIMUM LIKELIHOOD METHODS; MULTI-VIEW GEOMETRY; MULTI-VIEW IMAGING; MULTI-VIEWS; OBJECTIVE FUNCTIONS; OMNIDIRECTIONAL CAMERAS; OMNIDIRECTIONAL IMAGE; OVER-COMPLETE; OVERCOMPLETE DICTIONARIES; PROBABILISTIC MODELS; SCENE REPRESENTATION; SPARSE APPROXIMATIONS; SPARSE IMAGE REPRESENTATIONS; STEREO VIEW; STEREO-IMAGE; VISUAL INFORMATION;

CAMERAS; GEOMETRY; GESTURE RECOGNITION; LEARNING ALGORITHMS; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD ESTIMATION; OPTIMIZATION;

IMAGE MATCHING;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; AUTOMATED PATTERN RECOGNITION; COMPUTER ASSISTED DIAGNOSIS; IMAGE ENHANCEMENT; METHODOLOGY; PHOTOGRAPHY; REPRODUCIBILITY; SENSITIVITY AND SPECIFICITY; STATISTICAL ANALYSIS; STATISTICAL MODEL;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DATA INTERPRETATION, STATISTICAL; IMAGE ENHANCEMENT; IMAGE INTERPRETATION, COMPUTER-ASSISTED; LIKELIHOOD FUNCTIONS; PATTERN RECOGNITION, AUTOMATED; PHOTOGRAMMETRY; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY;

EID: 79952917189     PISSN: 10577149     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIP.2010.2081679     Document Type: Article

References (37)

1. R. I. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge, U.K.: Cambridge Univ. Press, 2000.
2. H.Wang, Y.Wexler, E. Ofek, and H. Hoppe, "Factoring repeated content within and among images," Proc. ACM SIGGRAPH, pp. 1-10, 2008.
3. I. Tošić and P. Frossard, "Geometry-based distributed scene representation with omnidirectional vision sensors," IEEE Trans. Image Process., vol. 17, no. 7, pp. 1033-1046, Jul. 2008.
4. B. A. Olshausen and D. Field, "Sparse coding with an overcomplete basis set: A strategy employed by V1?," Vis. Res., vol. 23, no. 37, pp. 3311-25, 1997. (Pubitemid 27493805)
5. K. Kreutz-Delgado, J. Murray, B. Rao, K. Engan, T.-W. Lee, and T. J. Sejnowski, "Dictionary learning algorithms for sparse representation," Neural Comput., vol. 15, no. 2, pp. 349-396, 2003. (Pubitemid 37049825)
6. M. Aharon, M. Elad, and A. Bruckstein, "K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation," IEEE Trans. Signal Process., vol. 54, no. 11, pp. 4311-4322, Nov. 2006. (Pubitemid 44637761)
7. B. A. Olshausen, "Learning sparse, overcomplete representations of time-varying natural images," in Proc. IEEE Int. Conf. Image Process., 2003.
8. B. A. Olshausen, C. Cadieu, B. J. Culpepper, and D. K. Warland, "Bilinear models of natural images," in Proc. SPIE Conf. Human Vis. Electron. Imag., 2007, pp. 1287-1294.
9. C. Cadieu and B. A. Olshausen, "Learning transformational invariants from time-varying natural images," in Proc. Conf. Neural Inf. Process. Syst., 2008, pp. 209-216.
10. B. A. Olshausen and D. J. Field, "Emergence of simple-cell receptive field properties by learning a sparse code for natural images," Nature, vol. 381, no. 6583, pp. 607-609, 1996. (Pubitemid 26177476)
11. K. Engan, S. Aase, and H. J. Hakon, "Method of optimal directions for frame design," in Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process., 1999, pp. 2443-2446.
12. K. Engan, B. D. Rao, and K. Kreutz-Delgado, "Frame design using FOCUSS with method of optimal directions (MOD)," in Proc. Norwegian Signal Process. Symp., 1999, pp. 1098-1112.
13. I. Gorodnitsky and B. Rao, "Sparse signal reconstruction from limited data using FOCUSS: A Re-weighted minimum norm algorithm," IEEE Trans. Signal Process., vol. 45, no. 3, pp. 600-616, Mar. 1997. (Pubitemid 127765947)
14. P. Schmid-Saugeon and A. Zakhor, "Dictionary design for matching pursuit and application to motion-compensated video coding," IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 6, pp. 880-886, Jun. 2004.
15. R. Gribonval and M. Nielsen, "Sparse representations in unions of bases," IEEE Trans. Inf. Theory, vol. 49, pp. 3320-3325, 2003.
16. P. Jost, P. Vandergheynst, S. Lesage, and R. Gribonval, "MoTIF: An efficient algorithm for learning translation invariant dictionaries," in Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process., 2006.
17. K. Engan, K. Skretting, and J. Husřy, "Family of iterative LS-based dictionary learning algorithms, ILS-DLA, for sparse signal representation," Digital Signal Process., vol. 17, no. 1, pp. 32-49, 2007. (Pubitemid 44828547)
18. G. Monaci, F. Sommer, and P. Vandergheynst, "Learning bimodal structure in audio-visual data," IEEE Trans. Neural Netw., vol. 20, no. 12, pp. 1898-1910, Dec. 2009.
19. P. Hoyer and A. Hyvärinen, "Independent component analysis applied to feature extraction from colour and stereo images," Netw.: Comput. Neural Syst., vol. 11, no. 3, pp. 191-210, 2000.
20. K. Okajima, "Binocular disparity encoding cells generated through an Infomax based learning algorithm," Neural Netw., vol. 17, no. 7, pp. 953-962, 2004. (Pubitemid 39093815)
21. I. Tošić and P. Frossard, "Coarse scene geometry estimation from sparse approximations of multi-view omnidirectional images," in Proc. Eur. Signal Process. Conf., 2007.
22. I. Tošić and P. Frossard, "Conditions for recovery of sparse signals correlated by local transforms," in Proc. IEEE Int. Symp. Inf. Theory, 2009, pp. 684-688.
23. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Royal Stat. Soc., vol. 39, no. 1, pp. 1-38, 1977.
24. R. M. Neal and G. E. Hinton, "A view of the EM algorithm that justifies incremental, sparse, and other variants," in Learning in Graphical Models, M. I. Jordan, Ed. New York: Kluwer, 1998, pp. 355-368.
25. B. J. Culpepper, "Learning 'What' and 'Where' From Movies," Master's, UC, Berkeley, 2007.
26. S. G. Mallat and Z. Zhang, "Matching pursuits with time-frequency dictionaries," IEEE Trans. Signal Process., vol. 41, no. 12, pp. 3397-3415, Dec. 1993.
27. I. V. R. M. Figueras, P. Vandergheynst, and P. Frossard, "Low rate and flexible image coding with redundant representations," IEEE Trans. Image Process., vol. 15, no. 3, pp. 726-739, Mar. 2006. (Pubitemid 43257570)
28. P. Frossard, "Robust and multiresolution video delivery: From H.26x to matching pursuit based technologies," Ph.D. dissertation, EPFL, Lausanne, Switzerland, 2000.
29. V. N. Temlyakov, "Weak greedy algorithms," Adv. Computat. Math., vol. 12, no. 2-3, pp. 213-227, 2000.
30. I. Tošić, "On unifying sparsity and geometry for image-based scene represenation," Ph.D. dissertation, EPFL, Lausanne, Switzerland, 2009.
31. I. Tošić, P. Frossard, and P. Vandergheynst, "Progressive coding of 3-D objects based on overcomplete decompositions," IEEE Trans. Circuits Syst. Video Technol., vol. 16, no. 11, pp. 1338-1349, Nov. 2006.
32. I. Tošić and P. Frossard, "Geometry-based distributed coding of multi-view omnidirectional images," in Proc. IEEE ICIP, 2008, pp. 2220-2223.
33. D. Varodayan, Y.-C. Liu, M. Flierl, and B. Girod, "Wyner-Ziv coding of multiview images with unsupervised learning of disparity and gray code," in Proc. Picture Coding Symp., 2007, pp. 1112-1115.
34. Y. Ma, S. Soatto, J. Košeckà, and S. S. Sastry, An Invitation to 3-D Vision: From Images to Geometric Models. New York: Springer, 2004.
35. M. Fischler and R. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography," Commun. ACM, vol. 24, no. 6, pp. 381-395, 1981. (Pubitemid 12444102)
36. D. Lowe, "Distinctive image features from scale-invariant keypoints," Int. J. Comput. Vis., vol. 60, no. 2, pp. 91-110, 2004.
37. J. Koseckà and X. Yang, "Global localization and relative pose estimation based on scale-invariant features," in Proc. Int. Conf. Pattern Recognit., 2004, pp. 319-322.