Name
Abstract | ||
|---|---|---|
We focus on the problem of estimating the ground plane orientation and location in monocular video sequences from a moving observer. Our only assumptions are that the 3D ego motion t and the ground plane normal n are orthogonal, and that n and t are smooth over time. We formulate the problem as a state-continuous Hidden Markov Model (HMM) where the hidden state contains t and n and may be estimated by sampling and decomposing homographies. We show that using blocked Gibbs sampling, we can infer the hidden state with high robustness towards outliers, drifting trajectories, rolling shutter and an imprecise intrinsic calibration. Since our approach does not need any initial orientation prior, it works for arbitrary camera orientations in which the ground is visible. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/CVPR.2014.442 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
hidden Markov models,image sampling,motion estimation,3D ego motion,HMM,arbitrary camera orientations,blocked Gibbs sampling,drifting trajectories,ground plane estimation,ground plane normal,ground plane orientation,homographies,imprecise intrinsic calibration,monocular video sequences,moving observer,outliers,rolling shutter,state-continuous hidden Markov model,ground plane,hidden markov model,visual gyroscope,visual odometry | Computer vision,Rolling shutter,Computer science,Outlier,Ground plane,Robustness (computer science),Artificial intelligence,Sampling (statistics),Hidden Markov model,Observer (quantum physics),Gibbs sampling | Conference |
Volume | Issue | ISSN |
2014 | 1 | 1063-6919 |
Citations | PageRank | References |
3 | 0.43 | 18 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ralf Dragon | 1 | 18 | 1.93 |
| Luc Van Gool | 2 | 27566 | 1819.51 |