Abstract | ||
---|---|---|
A local image transform based on cumulative similarity measures is defined and is shown to enable efficient correspondence and tracking near occluding boundaries. Unlike traditional methods, this transform allows correspondences to be found when the only contrast present is the occluding boundary itself and when the sign of contrast along the boundary is possibly reversed. The transform is based on the idea of a cumulative similarity measure which characterizes the shape of local image homogeneity; both the value of an image at a particular point and the shape of the region with locally similar and connected values is captured. This representation is insensitive to structure beyond an occluding boundary but is sensitive to the shape of the boundary itself, which is often an important cue. We show results comparing this method to traditional least-squares and robust correspondence matching. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1109/34.908973 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
traditional method,contrast present,local image homogeneity,traditional least-squares,local image,robust correspondence matching,cumulative similarity measure,occluding boundary,connected value,cumulative similiarity transforms,efficient correspondence,stereo,contrast,motion,cumulant,least square,robustness | Computer vision,Homogeneity (statistics),Similarity measure,Feature detection (computer vision),Pattern recognition,Computer science,Image matching,Artificial intelligence | Journal |
Volume | Issue | ISSN |
23 | 2 | 0162-8828 |
Citations | PageRank | References |
2 | 0.42 | 26 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Trevor Darrell | 1 | 22413 | 1800.67 |
Michele Covell | 2 | 706 | 78.42 |