Name
Abstract | ||
|---|---|---|
A fundamental open problem in computer vision—determining pose and correspondence between two sets of points in space—is solved with a novel, fast, robust and easily implementable algorithm. The technique works on noisy 2D or 3D point sets that may be of unequal sizes and may differ by non-rigid transformations. Using a combination of optimization techniques such as deterministic annealing and the softassign, which have recently emerged out of the recurrent neural network/statistical physics framework, analog objective functions describing the problems are minimized. Over thirty thousand experiments, on randomly generated points sets with varying amounts of noise and missing and spurious points, and on hand-written character sets demonstrate the robustness of the algorithm. |
Year | DOI | Venue |
|---|---|---|
1998 | 10.1016/S0031-3203(98)80010-1 | Pattern Recognition |
Keywords | DocType | Volume |
Point-matching,Pose estimation,Correspondence,Neural networks,Optimization,Softassign,Deterministic annealing,Affine transformation | Journal | 31 |
Issue | ISSN | Citations |
8 | 0031-3203 | 152 |
PageRank | References | Authors |
19.69 | 30 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Steven Gold | 1 | 864 | 83.13 |
| Lu, Chien-Ping | 2 | 152 | 19.69 |
| A Rangarajan | 3 | 3698 | 367.52 |
| Pappu, Suguna | 4 | 152 | 19.69 |
| Eric Mjolsness | 5 | 1058 | 140.00 |