Abstract | ||
---|---|---|
In this paper, we revisit the perspective-n-line problem and propose a closed-form solution that is fast, robust and generally applicable. Our main idea is to formulate the pose estimation problem into an optimal problem. Our method only needs to solve a fifteenth-order and a fourth-order univariate polynomial, respectively, which makes the processes more easily understood and significantly improves the performance. Experiment results show that our method offers accuracy and precision comparable or better than existing state-of-the-art methods, but with significantly lower computational cost. This superior computational efficiency is particularly suitable for real applications. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/s00138-019-01012-0 | Machine Vision and Applications |
Keywords | Field | DocType |
Perspective-n-line problem (PnL), Camera pose estimation, Absolute position and orientation, Computer vision | Computer vision,Polynomial,Computer science,Pose,Artificial intelligence,Accuracy and precision,Univariate | Journal |
Volume | Issue | ISSN |
30 | 4 | 1432-1769 |
Citations | PageRank | References |
2 | 0.38 | 16 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ping Wang | 1 | 93 | 44.15 |
Guili Xu | 2 | 5 | 1.13 |
Yuehua Cheng | 3 | 46 | 5.76 |
Qida Yu | 4 | 5 | 1.47 |