Open oleg-alexandrov opened 9 years ago
Hi Oleg, How many features are you using to train a vocab tree? You should have fewer leaves in the tree (by maybe a factor of 10) relative to the number of features used to learn the visual words.
Noah, thank you. So, depth = 0, branching factor = number_features/10. I will play with these at some point, then perhaps I will add a blurb in the Readme file.
One minor thing I noticed is that the branching factor can be tricky to set. The recommended value of 500000 in my experience results in an image matching well to itself but not to its neighbors from a video sequence. Perhaps some heuristics could be used here, maybe the square root of number of features?