Class for computing stereo correspondence using the semi-global block matching algorithm

The class implements the modified H. Hirschmuller algorithm [HH08] that differs from the original one as follows:

• By default, the algorithm is single-pass, which means that you consider only 5 directions instead of 8. Set Mode='HH' in the contructor to run the full variant of the algorithm but beware that it may consume a lot of memory.

• The algorithm matches blocks, not individual pixels. Though, setting BlockSize=1 reduces the blocks to single pixels.

• Mutual information cost function is not implemented. Instead, a simpler Birchfield-Tomasi sub-pixel metric from [BT96] is used. Though, the color images are supported as well.

• Some pre- and post- processing steps from K. Konolige algorithm cv.StereoBM are included, for example: pre-filtering (XSobel type) and post-filtering (uniqueness check, quadratic interpolation and speckle filtering).

Usage

bm = cv.StereoSGBM('MinDisparity',0, ...);
bm.BlockSize = ...;
disparity = bm.compute(left, right);

References

[HH08]:

Heiko Hirschmuller. "Stereo processing by semiglobal matching and mutual information". Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(2):328-341, 2008.

[BT96]:

Stan Birchfield and Carlo Tomasi. "A pixel dissimilarity measure that is insensitive to image sampling". Pattern Analysis and Machine Intelligence, IEEE Transactions on, 20(4):401-406, 1998.