Hi, I was taking another look on a paper published in Computers and GeoSciences on something called a 'Variance Quadtree' algorithm[1]. The main idea is to recursively partition an image into smaller and smaller rectangles, based on the amount of variance within each rectangle. Thus, regions of more variation get split into smaller nested rectangles.
The source code for the algorithm is given in Matlab source[2]. I have tried unsuccessfully to port the code to R, mostly because I do not completely understand several of the matlab matrix idioms used in the code. I think that a C version of the algorithm, along with some minor modifications to convert the quadtree structure into GRASS vectors (similar to what v.surf.rst can output) would be a nice addition to imagery analysis in GRASS. Anyone want to give some pointers / help on porting this to C? The algorithm is relatively simple, however some of the matlab-specific matrix operations may be a challenge. 1. http://dx.doi.org/10.1016/j.cageo.2006.08.009 2. http://www.usyd.edu.au/su/agric/acpa/software/matlab/vqt_matlab.zip Cheers, Dylan -- Dylan Beaudette Soil Resource Laboratory http://casoilresource.lawr.ucdavis.edu/ University of California at Davis 530.754.7341 _______________________________________________ grass-dev mailing list [email protected] http://lists.osgeo.org/mailman/listinfo/grass-dev
