Name
Abstract | ||
|---|---|---|
We present a new form of least squares (LS), called ``hyper LS'', for geometric problems that frequently appear in computer vision applications. Doing rigorous error analysis, we maximize the accuracy by introducing a normalization that eliminates statistical bias up to second order noise terms. Our method yields a solution comparable to maximum likelihood (ML) without iterations, even in large noise situations where ML computation fails. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ICPR.2010.10 | Pattern Recognition |
Keywords | Field | DocType |
least mean squares methods,statistical analysis,geometric problem,hyper least squares method,statistical bias,ellipse fitting,fundamental matrix,geometric fitting,homography,least squares,maximum likelihood | Least squares,Normalization (statistics),Maximum likelihood,Homography,Artificial intelligence,Fundamental matrix (computer vision),Computation,Mathematical optimization,Pattern recognition,Algorithm,Geometric problems,Covariance matrix,Mathematics | Conference |
ISSN | ISBN | Citations |
1051-4651 | 978-1-4244-7542-1 | 1 |
PageRank | References | Authors |
0.37 | 11 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Prasanna Rangarajan | 1 | 34 | 2.97 |
| Kenichi Kanatani | 2 | 1468 | 320.07 |
| Hirotaka Niitsuma | 3 | 4 | 1.45 |
| Yasuyuki Sugaya | 4 | 267 | 25.45 |