13.7 General References

Chapter Contents (Back)
Matching, 3-D General.

Fischler, M.A., and Bolles, R.C.,
Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,
CACM(24), No. 6, June 1981, pp. 381-395. BibRef 8106
And: RCV87(726-740). BibRef
Earlier: DARPA80(71-88). BibRef
And: SRI-TN-213, March 1980.
WWW Version. RANSAC. Robust Technique. BibRef
And:
A RANSAC-Based Approach to Model Fitting and Its Application to Finding Cylinders in Range Data,
IJCAI81(637-643). RANSAC algorithm for matching data points to the model. This allows error points to be eliminated and thus ignored - find a match that a majority of the points are happy with. BibRef

Bolles, R.C.,
Robust Feature Matching Through Maximal Cliques,
SPIE(182), Imaging Applications for Automated Industrial Inspection and Assembly, 1979, pp. 140-149. BibRef 7900

Roth, G.[Gerhard], and Levine, M.D.[Martin D.],
Minimal Subset Random Sampling for Pose Determination and Refinement,
AMV Strategies921992, pp. 1-21. RANSAC. See also Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. RANSAC is good and can be generalized and extended. BibRef 9200

Suetens, P., Fua, P.V., and Hanson, A.J.,
Some Computational Strategies for Object Recognition,
Surveys(24), No. 1, March 1992, pp. 5-62. Survey, Matching. Matching, Survey. Covers a number of different recognition techniques both from SRI and many other locations. The survey is dated to about 1989. BibRef 9203

Lindenbaum, M.,
Bounds on Shape-Recognition Performance,
PAMI(17), No. 7, July 1995, pp. 666-680.
IEEE Abstract. IEEE Top Reference.
WWW Version. Evaluation, Matching. Analysis of the shape matching task, no matter what the method, to determin how good it can be. BibRef 9507

Lindenbaum, M.[Michael], Ben-David, S.[Shai],
VC-Dimension Analysis of Object Recognition Tasks,
JMIV(10), No. 1, January 1999, pp. 27-49.
WWW Version. Model-based recognition and learning. BibRef 9901
Earlier:
Applying VC-Dimension Analysis to Object Recognition,
ECCV94(A:237-250).
Springer DOI Link BibRef
And:
Applying VC-Dimension Analysis to 3D Object Recognition from Perspective Projections,
AAAI-94(985-991). BibRef

Shum, H.Y., Ikeuchi, K., Reddy, R.,
Principal Component Analysis with Missing Data and Its Application to Polyhedral Object Modeling,
PAMI(17), No. 9, September 1995, pp. 854-867.
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 9509
And: MfR01(Chapter I-1). BibRef
Earlier:
Principal Component Analysis with Missing Data and Its Application to Object Modeling,
CVPR94(560-565).
IEEE Abstract. IEEE Top Reference. BibRef
And:
Virtual Reality Modeling from a Sequence of Range Images,
ARPA94(II:1189-1198). BibRef

Liu, G.[Gang], Haralick, R.M.[Robert M.],
Optimal matching problem in detection and recognition: Performance Evaluation,
PR(35), No. 10, October 2002, pp. 2125-2139.
WWW Version. 0206
BibRef

Kay, S.M., Gabriel, J.R.,
An invariance property of the generalized likelihood ratio test,
SPLetters(10), No. 12, December 2003, pp. 352-355.
IEEE Abstract. IEEE Top Reference. 0401
Generalized likelihood ratio test (GLRT) is invariant with respect to transformations for which the hypothesis testing problem itself is invariant. BibRef

Li, H.Z.[Hao-Zheng], Liu, Z.Q.A.[Zhi-Qi-Ang], Zhu, X.H.[Xiang-Hua],
Hidden Markov models with factored Gaussian mixtures densities,
PR(38), No. 11, November 2005, pp. 2022-2031.
WWW Version. 0509
BibRef

Nistér, D.[David],
Preemptive RANSAC for live structure and motion estimation,
MVA(16), No. 5, December 2005, pp. 321-329.
Springer DOI Link 0601
BibRef
Earlier: ICCV03(199-206).
IEEE DOI Link 0311
BibRef

Kuhnert, M.[Matthias], Voinov, A.[Alexey], Seppelt, R.[Ralf],
Comparing Raster Map Comparison Algorithms for Spatial Modeling and Analysis,
PhEngRS(71), No. 8, August 2005, pp. 975-984.
WWW Version. 0602
A review of existing algorithms to compare spatial patterns and development of a new approach based on the expanding window approach. BibRef

Cheng, C.M.[Chia-Ming], Lai, S.H.[Shang-Hong],
A consensus sampling technique for fast and robust model fitting,
PR(42), No. 7, July 2009, pp. 1318-1329.
Elsevier DOI Link
WWW Version. 0903
RANSAC; Robust estimation; Model fitting; Fundamental matrix estimation BibRef


Choi, J.M.[Jong-Moo], Medioni, G.[Gerard],
StaRSaC: Stable random sample consensus for parameter estimation,
CVPR09(675-682).
IEEE DOI Link 0906
BibRef

Raguram, R.[Rahul], Frahm, J.M.[Jan-Michael], Pollefeys, M.[Marc],
A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus,
ECCV08(II: 500-513).
Springer DOI Link 0810
BibRef

Toldo, R.[Roberto], Castellani, U.[Umberto], Fusiello, A.[Andrea],
A Bag of Words Approach for 3D Object Categorization,
MIRAGE09(116-127).
Springer DOI Link 0905
BibRef

Toldo, R.[Roberto], Fusiello, A.[Andrea],
Automatic Estimation of the Inlier Threshold in Robust Multiple Structures Fitting,
CIAP09(123-131).
Springer DOI Link 0909
BibRef
Earlier:
Robust Multiple Structures Estimation with J-Linkage,
ECCV08(I: 537-547).
Springer DOI Link 0810
Deal with multiple instances of the same structure, which complicate RANSAC operation. BibRef

Marquez-Neila, P.[Pablo], Miro, J.G.[Jacobo Garcia], Buenaposada, J.M.[Jose M.], Baumela, L.[Luis],
Improving RANSAC for fast landmark recognition,
VisLoc08(1-8).
IEEE DOI Link 0806
BibRef

Fan, L.X.[Li-Xin], Pylvänäinen, T.[Timo],
Robust Scale Estimation from Ensemble Inlier Sets for Random Sample Consensus Methods,
ECCV08(III: 182-195).
Springer DOI Link 0810
BibRef
Earlier: A2, A1:
Hill Climbing Algorithm for Random Sample Consensus Methods,
ISVC07(I: 672-681).
Springer DOI Link 0711
BibRef

Yao, B.[Benjamin], Yang, X.[Xiong], Zhu, S.C.[Song-Chun],
Introduction to a Large-Scale General Purpose Ground Truth Database: Methodology, Annotation Tool and Benchmarks,
EMMCVPR07(169-183).
Springer DOI Link 0708
BibRef

Leung, A.P.[Alex Po], Gong, S.G.[Shao-Gang],
Optimizing Distribution-based Matching by Random Subsampling,
CVPR07(1-8).
IEEE DOI Link 0706
BibRef

Zhang, W.[Wei], Kosecka, J.[Jana],
Generalized RANSAC Framework for Relaxed Correspondence Problems,
3DPVT06(854-860).
IEEE DOI Link 0606
BibRef

Rodehorst, V.[Volker], Hellwich, O.[Olaf],
Genetic Algorithm SAmple Consensus (GASAC): A Parallel Strategy for Robust Parameter Estimation,
RANSAC06(103).
IEEE DOI Link 0609
BibRef

Subbarao, R.[Raghav], Meer, P.[Peter],
Beyond RANSAC: User Independent Robust Regression,
RANSAC06(101).
IEEE DOI Link 0609
BibRef

Frahm, J.M.[Jan-Michael], Pollefeys, M.[Marc],
RANSAC for (Quasi-)Degenerate data (QDEGSAC),
CVPR06(I: 453-460).
IEEE DOI Link 0606
BibRef

Capel, D.P.,
An Effective Bail-out Test for RANSAC Consensus Scoring,
BMVC05(xx-yy).
HTML Version. 0509
BibRef

Zuliani, M., Kenney, C.S., Manjunath, B.S.,
The Multiransac Algorithm and its Application to Detect Planar Homographies,
ICIP05(III: 153-156).
IEEE DOI Link 0512
BibRef

Rozenfeld, S.[Stas], Shimshoni, I.[Ilan],
The Modified pbM-Estimator Method and a Runtime Analysis Technique for the RANSAC Family,
CVPR05(I: 1113-1120).
IEEE DOI Link 0507
See also Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. BibRef

Basri, R.,
On the Uniqueness of Correspondence under Orthographic and Perspective Projections,
DARPA92(875-884). BibRef 9200
And: MIT AI Memo-1330, December 1991.
WWW Version. Epi-polar lines define the affine transformation. BibRef

Weinshall, D., and Basri, R.,
Distance Metric between 3D Models and 2D Images for Recognition and Classification,
PAMI(18), No. 4, April 1996, pp. 465-479.
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 9604
Earlier: CVPR93(220-225).
IEEE Abstract. IEEE Top Reference. BibRef
Earlier: A2, A1: MIT AI Memo-1373, July 1992.
WWW Version. Compute transformation based metrics that penalize the amount of tranformation needed for the match. Optimal for affine deformations. BibRef

Ponce, J., Bajcsy, R., Metaxas, D.N., Binford, T.O., Forsyth, D.A., Hebert, M., Ikeuchi, K., Kak, A.C., Shapiro, L.G., Slaroff, S., Pentland, A.P., and Stockman, G.C.,
Object Representation for Object Recognition,
CVPR94(147-152).
IEEE Abstract. IEEE Top Reference. BibRef 9400 Panel DiscussionReport on the workshop panel. BibRef

Yacoob, Y., and Gold, Y.I.,
3D Object Recognition Via Simulated Particles Diffusion,
CVPR89(442-449).
IEEE Abstract. IEEE Top Reference. Recognize Three-Dimensional Objects. Characterize shapes as a diffusion-like process. Find the rotation and translation for the 3-D object. BibRef 8900

Stockman, G.C.,
Object Recognition,
AIRI90(225-253). BibRef 9000

Bhanu, B.[Bir], and Burger, W.[Wilhelm],
Signal-to-Symbol Conversion for Structural Object Recognition Using Hidden Markov Models,
ARPA94(II:1287-1291). It seems to say the problem remains. BibRef 9400

Gilmore, J.F., Pemberton, W.B.,
A Survey of Aircraft Classification Algorithms,
ICPR84(559-561). BibRef 8400

Kanazawa, Y.S.[Yasu-Shi], Kanatani, K.[Kenichi],
Do We Really Have to Consider Covariance Matrices for Image Features?,
ICCV01(II: 301-306).
IEEE DOI Link 0106
Issues in matching and use of the match results. BibRef

Chapter on Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants continues in
String Matching .


Last update:Nov 16, 2009 at 19:35:14