Closed jsherrah closed 11 years ago
Having read that paper, it's rooly complicated. Since the emphasis at the mo is on the CRFs, I will use a simpler approach. The unary potentials will be some classifier or probabilistic model of the local texture per class. We can start with something really simple, like HOG and/or colour histograms, and then add complexity until finally reproducing state of the art (which is unlikely to be a 2006 paper).
Shotton 2006 uses Boykov and Jolly 2001 for inference. B&J use a new max flow method from their comparison paper. This is the Boykov, Kolmogorov C implementation that seems to get used everywhere (ALE, PyMaxflow).
I have just realised PyMaxflow can do multi-class labelling and alpha expansion using fastmin:
maxflow.fastmin.aexpansion_grid(D, V, max_cycles=None, labels=None)
Let's continue to use PyMaxflow.
Created a 3-class example (foreground "midground" and background). We could close this issue, noting that the example model is simple.
PyMaxflow's alpha expansion and alpha-beta swap methods accept pairwise potentials between class-labels - not between label variables/nodes.
Probably need to move away from PyMaxflow long term. May need other approximate inference techniques (belief propagation, MCMC).
let's close it once we have a labelling on the ms data set.
Hey J, how do you feel about closing this issue now? We've got N-class working on the MSRC dataset now, and even have superpixels.
Ok
Sent from my iPad
On Aug 19, 2013, at 8:08 AM, Ant B notifications@github.com wrote:
Hey J, how do you feel about closing this issue now? We've got N-class working on the MSRC dataset now, and even have superpixels.
— Reply to this email directly or view it on GitHub.
create file sceneLabelN.py to do multi-class scene labels with first-order potentials.
The plan is to reproduce the work of Shotton et al, ECCV 2006:
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.83.519
Probably use stair vision library, but needs investigation.