Abstract | ||
---|---|---|
Image alignment should be based on features that are robust with respect to phenomena such as global illumination changes, shading variations, and local highlights. While hue provides a natural degree of invariance to these phenomena, we show that it has several deficiencies in terms of gradient-based image alignment. To overcome these limitations, we introduce a 2D representation for hue that maintains a highly compressed representation for saturation. This allows the representation to model gray without sacrificing the desirable properties of hue. We show that our approach has a more consistent local domain of convergence when used for gradient-based alignment, and demonstrate its use in the context of a probabilistic motion-based tracker. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICPR.2002.1048394 | Pattern Recognition, 2002. Proceedings. 16th International Conference |
Keywords | DocType | Volume |
gradient methods,image colour analysis,image matching,image representation,image segmentation,image sequences,motion estimation,stereo image processing,2D representation,global illumination changes,gradient-based image alignment,gray modeling,highly compressed representation,hue,image alignment,image mosaicing,local domain of convergence,local highlights,motion estimation,probabilistic motion-based tracker,saturated independent color coordinates,shading variations,stereo | Conference | 2 |
ISSN | Citations | PageRank |
1051-4651 | 0 | 0.34 |
References | Authors | |
1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thomas F. El-maraghi | 1 | 0 | 0.34 |
Jepson, A.D. | 2 | 402 | 81.91 |