Name
Abstract | ||
|---|---|---|
The interpretation of the 3D world from image sequences requires the identification and correspondences of key features in the scene. We describe a robust algorithm for matching groupings of features related to the objects in the scene. We consider the propagation of uncertainty from the feature detection stage through the grouping stage to provide a measure of uncertainty at the matching stage. We focus upon indoor scenes and match junctions, which are groupings of line segments that meet at a single point. A model of the uncertainty in junction detection is described, and the junction uncertainty under the epipolar constraint is determined. Junction correspondence is achieved through matching of each line segment associated with the junction. A match likelihood is then derived based upon the detection uncertainties and then combined with information on junction topology to create a similarity measure. A robust matching algorithm is proposed and used to match junctions between pairs of images. The presented experimental results on real images show that the matching algorithm produces sufficiently reliable results for applications such as structure from motion |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/34.895973 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
line segment,junction detection,3d world,image matching,match likelihood,uncertainty propagation,grouping,junction correspondence,feature groupings,junction topology,indoor scenes,robust algorithm,feature extraction,robust matching algorithm,image sequences,uncertainty handling,junction uncertainty,feature detection stage,matching algorithm,detection uncertainties,detection uncertainty,matching stage,image motion analysis,feature detection,junction,epipolar geometry,topology,layout,robustness,application software,computer vision,tracking,image segmentation,structure from motion,uncertainty | Structure from motion,Line segment,Computer vision,Propagation of uncertainty,Similarity measure,Pattern recognition,Epipolar geometry,Computer science,Feature extraction,Artificial intelligence,Real image,Blossom algorithm | Journal |
Volume | Issue | ISSN |
22 | 12 | 0162-8828 |
Citations | PageRank | References |
7 | 0.50 | 23 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xinquan Shen | 1 | 39 | 5.77 |
| Phil Palmer | 2 | 7 | 0.50 |