Name
Abstract | ||
|---|---|---|
We present a linear method for global camera pose registration from pair wise relative poses encoded in essential matrices. Our method minimizes an approximate geometric error to enforce the triangular relationship in camera triplets. This formulation does not suffer from the typical `unbalanced scale' problem in linear methods relying on pair wise translation direction constraints, i.e. an algebraic error, nor the system degeneracy from collinear motion. In the case of three cameras, our method provides a good linear approximation of the trifocal tensor. It can be directly scaled up to register multiple cameras. The results obtained are accurate for point triangulation and can serve as a good initialization for final bundle adjustment. We evaluate the algorithm performance with different types of data and demonstrate its effectiveness. Our system produces good accuracy, robustness, and outperforms some well-known systems on efficiency. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICCV.2013.66 | ICCV |
Keywords | Field | DocType |
trifocal tensor,global linear method,bundle adjustment,multiple camera,image coding,camera triplet,multiple-camera registration,camera pose registration,pair wise relative,structure-from-motion,good linear approximation,matrix algebra,global camera,linear method,approximate geometric error minimization,global camera pose registration,algebraic error,pair wise translation direction constraints,approximate geometric error,point triangulation,pose estimation,pair wise relative pose encoding,essential matrices,cameras,good accuracy,image registration,camera triplets,tensors,good initialization,unbalanced scale problem | Linear approximation,Computer vision,Computer science,Bundle adjustment,Pose,Robustness (computer science),Triangulation (social science),Artificial intelligence,Initialization,Image registration,Trifocal tensor | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
29 | 0.76 | 34 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nianjuan Jiang | 1 | 128 | 7.27 |
| Zhaopeng Cui | 2 | 93 | 16.66 |
| Ping Tan | 3 | 1739 | 86.98 |