Abstract | ||
---|---|---|
In this paper we investigate the quality of 3D-2D pose estimates using hand labeled line and point correspondences. We select point correspondences from junctions in the image, allowing to construct a meaningful interpretation about how the junction is formed, as proposed in e.g. [1], [2], [3]. We make us of this information referred as the semantic interpretation, to identify the different types of junctions (i.e. L-junctions and T-junctions). T-junctions often denote occluding contour, and thus do not designate a point in space. We show that the semantic interpretations is useful for the removal of these T-junction from correspondence sets, since they have a negative effect on motion estimates. Furthermore, we demonstrate the possibility to derive additional line correspondences from junctions using the semantic interpretation, providing more constraints and thereby more robust estimates. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-76858-6_67 | ISVC (1) |
Keywords | Field | DocType |
point correspondence,negative effect,robust estimate,correspondence set,motion estimate,denote occluding contour,additional line correspondence,meaningful interpretation,different type,semantic interpretation,pose estimation,robust estimator,motion estimation | Computer vision,Point correspondence,Pattern recognition,Computer science,Semantic interpretation,Pose,Rigid body,Artificial intelligence,Stereo image | Conference |
Volume | ISSN | ISBN |
4841 | 0302-9743 | 3-540-76857-2 |
Citations | PageRank | References |
1 | 0.35 | 9 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Florian Pilz | 1 | 15 | 1.98 |
Yan Shi | 2 | 1 | 0.35 |
Daniel Grest | 3 | 129 | 10.65 |
Nicolas Pugeault | 4 | 403 | 24.07 |
Sinan Kalkan | 5 | 313 | 31.83 |
Norbert Krüger | 6 | 312 | 19.80 |