Abstract | ||
---|---|---|
This paper approaches the problem of finding correspondences between images in which there are large changes in viewpoint, scale and illumi- nation. Recent work has shown that scale-space 'interest points' may be found with good repeatability in spite of such changes. Further- more, the high entropy of the surrounding image regions means that local descriptors are highly discriminative for matching. For descrip- tors at interest points to be robustly matched between images, they must be as far as possible invariant to the imaging process. In this work we introduce a family of features which use groups of interest points to form geometrically invariant descriptors of image regions. Feature descriptors are formed by resampling the image rel- ative to canonical frames defined by the points. In addition to robust matching, a key advantage of this approach is that each match implies ah ypothesis of the local 2D (projective) transformation. This allows us to immediately reject most of the false matches using a Hough trans- form. We reject remaining outliers using RANSAC and the epipolar constraint. Results show that dense feature matching can be achieved in a few seconds of computation on 1GHz Pentium III machines. |
Year | Venue | Keywords |
---|---|---|
2002 | BMVC | image processing,scale space |
Field | DocType | Citations |
Computer vision,Epipolar geometry,Pattern recognition,RANSAC,Computer science,Outlier,Invariant (mathematics),Artificial intelligence,Discriminative model,Resampling,Entropy (information theory),Computation | Conference | 193 |
PageRank | References | Authors |
34.76 | 12 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
M. Brown | 1 | 2474 | 175.45 |
D. G. Lowe | 2 | 15718 | 1413.60 |