Name
Abstract | ||
|---|---|---|
This paper presents a similarity-based adaptive neighborhood (SBAN) dense stereovision algorithm which uses color for comparing pixels. In SBAN methods, the neighbor pixels which are not similar to the central one are excluded of the window when computing the correlation index, which corresponds to adapting the equivalent size and shape of the correlation neighborhood. We present a specific type of SBAN algorithms, in which the similarity criterion is based on a pre-classification of pixels, and show that they can be efficiently implemented using recursive computations. As an example, we show that color, more precisely hue, is an efficient similarity criterion for SBAN methods and present the result on a classical stereo pair. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1007/1-4020-4179-9_79 | COMPUTER VISION AND GRAPHICS (ICCVG 2004) |
Keywords | Field | DocType |
SBAN stereovision, recursive implementation | Pattern recognition,Similarity criterion,Kleene's recursion theorem,Hue,Algorithm,Correlation,Pixel,Artificial intelligence,Recursive computation,Mathematics,Recursion | Conference |
Volume | Citations | PageRank |
32 | 1 | 0.39 |
References | Authors | |
4 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Madaín Pérez-Patricio | 1 | 1 | 0.39 |
| Olivier Colot | 2 | 129 | 15.55 |
| Francois Cabestaing | 3 | 8 | 2.39 |