this is for holding javascript data
Iv Sjsn edited untitled.tex
about 9 years ago
Commit id: a4a127739d33bbf65b613887f84f9ee6ad80a6a6
deletions | additions
diff --git a/untitled.tex b/untitled.tex
index d636b63..5490970 100644
--- a/untitled.tex
+++ b/untitled.tex
...
We partition the video volume into $C^N$ non-overlapping regions using GBH segmentation. The segmentation is based on appearance and motion similarity between the local regions. Each segment $c_i \in C^N$ is comprised of arbitrary shape & sized cloud of points $x_i=\{x^0_i, x^1_i, ...., x^P_i\}$ in video volume space $\mathbb{R}^3$.
The practical challenge is to represent segment $c_i$ efficiently without comprimising on the memory and accuracy. Because it is difficult to fit regular structure such as 3D bounding box or ellipsiod. So we came up with solution to divide the video into regular
shaped $m \times m \times m$
grids sized cells and construct the representation based on such structure. It does reduce the memory load by $m^3$ times. Also such
grids cells can
be constructed act like a building block to
represent construct arbitrary shape and sized 3D regions.