Dynamic programming on a scanline is one of the oldest and still popular methods for stereo correspondence. While efficient, its performance is far from the state of the art because the vertical consistency between the scanlines is not enforced. We re-examine the use of dynamic programming for stereo correspondence by applying it to a tree structure, as opposed to the individual scanlines. The nodes of this tree are all the image pixels, but only the "most important" edges of the 4 connected neighbourhood system are included. Thus our algorithm is truly a global optimization method because disparity estimate at one pixel depends on the disparity estimates at all the other pixels, unlike the scanline based methods. We evaluate our algorithm on the benchmark Middlebury database. The algorithm is very fast; it takes only a fraction of a second for a typical image. The results are considerably better than that of the scanline based methods. While the results are not the state of the art, our algorithm offers a good trade off in terms of accuracy and computational efficiency.
Stereo correspondence by dynamic programming on a tree
2005-01-01
184712 byte
Conference paper
Electronic Resource
English
A Fast Line Segment Based Dense Stereo Algorithm Using Tree Dynamic Programming
British Library Conference Proceedings | 2006
|Image Stereo Correspondence Method for Stereo Vision
Trans Tech Publications | 2013
|A Fast Line Segment Based Dense Stereo Algorithm Using Tree Dynamic Programming
Springer Verlag | 2006
|Stereo matching using weighted dynamic programming on a single-direction four-connected tree
British Library Online Contents | 2012
|Dense stereo using pivoted dynamic programming
British Library Online Contents | 2004
|