12.1.6.2 Relaxation Based Techniques

Chapter Contents (Back)
Matching, Points. Matching, Relaxation. Relaxation, Matching.

Ranade, S., and Rosenfeld, A.,
Point Pattern Matching by Relaxation,
PR(12), No. 4, 1980, pp. 269-275.
WWW Link. Relaxation. The input is two sets of points, each corresponding to feature locations in different views of the scene. Like Kahl( See also Some Experiments in Point Pattern Matching. ), the system finds a global displacement (translation) that best fits the data, but works better with small rotation and scale changes. Points are matched with all points in the other image with the match rating based on how many other point matches agree with the transform computed from that match. The scores are computed (and updated) based on the scores of the other point pairs to produce a highly rated consensus transform for the set of points. BibRef 8000

Wang, C.Y.[Cheng-Ye], Sun, H.F.[Han-Fang], Yada, S.[Shiro], and Rosenfeld, A.,
Some Experiments in Relaxation Image Matching Using Corner Features,
PR(16), No. 2, 1983, pp. 167-182.
WWW Link. BibRef 8300
Earlier: UMD-CS TR-1-71. Relaxation. A relaxation procedure is used to find matches between pairs of images that differ in position and orientation. The matching is performed on sets of feature points (corners), which have position, orientation, contrast, and sharpness. After several iterations, good matches are clustered which gives sets of transformations (translation and rotation). The best transformation can be selected from these likely ones. This extends an earlier method See also Point Pattern Matching by Relaxation. BibRef

Ogawa, H.,
Labeled Point Pattern Matching by Fuzzy Relaxation,
PR(17), No. 5, 1984, pp. 569-573.
WWW Link. BibRef 8400

Ogawa, H.,
Labeled Point Pattern Matching by Delaunay Triangulation and Maximal Cliques,
PR(19), No. 1, 1986, pp. 35-40.
WWW Link. BibRef 8600

Kitchen, L.,
Relaxation for Point-Pattern Matching: What it really Computes,
CVPR85(405-407). Univ. of Massachusetts. Preliminary. BibRef 8500

Sang, N., Zhang, T.X.,
Rotation and Scale Change Invariant Point Pattern Relaxation Matching by the Hopfield Neural Network,
OptEng(36), No. 12, December 1997, pp. 3378-3385. 9801
BibRef

12.1.6.3 Long Sequences, Motion Matching

Chapter Contents (Back)
Tracking. Matching, Points. Matching, Sequence. Motion, Matching. See also Long Sequence Matching and Motion.

Mohanty, N.C.,
Computer Tracking of Moving Point Targets in Space,
PAMI(3), No. 5, September 1981, pp. 606-611. BibRef 8109

Sethi, I.K., and Jain, R.C.,
Finding Trajectories of Feature Points in a Monocular Image Sequence,
PAMI(9), No. 1, January 1987, pp. 56-73. BibRef 8701
Earlier: CAIA85(106-111). BibRef
And: A2, A1:
Establishing Correspondence of Non-Rigid Objects Using Smoothness of Motion,
CVWS84(83-87). This is primarily a long sequence correspondence problem. Initial matches are generated based on nearest neighbors, then matches are exchanged until it is stable. Exchanges are made to increase the smoothness of motion criteria. BibRef

Chen, H.H., and Huang, T.S.,
Using Motion from Orthographic Views to Verify 3-D Point Matches,
PAMI(13), No. 9, September 1991, pp. 872-878.
IEEE DOI BibRef 9109
Earlier:
Using Motion from Orthographic Projections to Prune 3-D Point Matches,
Motion89(290-297). Matching, Sequence. Since it is orthographic, ignore Z and use only the X and Y components. See also Motion and Structure from Orthographic Projections. BibRef

Bruckstein, A.M., and Netravali, A.N.,
On Minimal Energy Trajectories,
CVGIP(49), No. 3, March 1990, pp. 283-296.
WWW Link. Also see curve fitting papers (snakes and the like). BibRef 9003

Salari, V., and Sethi, I.K.,
Feature Point Correspondence in the Presence of Occlusion,
PAMI(12), No. 1, January 1990, pp. 87-91.
IEEE DOI BibRef 9001
Earlier:
Correspondence in Presence of Occlusion,
CVWS87(327-330). A modification of See also Finding Trajectories of Feature Points in a Monocular Image Sequence. BibRef

Sethi, I.K., Salari, V., Vemuri, S.,
Feature Point Matching in Image Sequences,
PRL(7), 1988, pp. 113-121. BibRef 8800

Sethi, I.K., Salari, V., Vemuri, S.,
Image Sequence Segmentation Using Motion Coherence,
ICCV87(667-671). BibRef 8700

Sethi, I.K., Patel, N.V., Yoo, J.H.,
A General Approach for Token Correspondence,
PR(27), No. 12, December 1994, pp. 1775-1786.
WWW Link. BibRef 9412

Sethi, I.K., Ramesh, N.,
Local Association Based Recognition of Two-Dimensional Objects,
MVA(5), 1992, pp. 265-276. BibRef 9200

Aloimonos, Y.[Yiannis], Tsakiris, D.P.[Dimitris P.],
On the Visual Mathematics of Tracking,
IVC(9), No. 4, August 1991, pp. 235-251.
WWW Link. BibRef 9108
Earlier:
Tracking in a complex visual environment,
ECCV90(247-258).
Springer DOI 9004
BibRef

Sudhir, G., Banerjee, S., Zisserman, A.,
Finding Point Correspondences in Motion Sequences Preserving Affine Structure,
CVIU(68), No. 2, November 1997, pp. 237-246.
DOI Link 9712
BibRef
Earlier: BMVC93(xx-yy).
PDF File. BibRef

Mehrotra, R.,
Establishing Motion-Based Feature Point Correspondence,
PR(31), No. 1, January 1998, pp. 23-30.
WWW Link. 9802
BibRef


Mooser, J.[Jonathan], You, S.[Suya], Neumann, U.[Ulrich], Grasset, R.[Raphael], Billinghurst, M.[Mark],
A Dynamic Programming Approach to Maximizing Tracks for Structure from Motion,
ACCV09(II: 1-10).
Springer DOI 0909
BibRef

Cheng, C.L., and Aggarwal, J.K.,
A Two-Stage Hybrid Approach to the Correspondence Problem Via Forward-Searching and Backward-Correcting,
ICPR90(I: 173-179).
IEEE DOI Matching long sequences of point patterns using motion knowledge (uncertainty inversely proportional to velocity). BibRef 9000

Chapter on Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces continues in
Principal Component Decompositions, Point features .


Last update:Mar 13, 2017 at 16:25:24