this is for holding javascript data
Iv Sjsn edited untitled.tex
almost 9 years ago
Commit id: 777bdecaf5671e98a70aafb0109cc6dd78a22e91
deletions | additions
diff --git a/untitled.tex b/untitled.tex
index 5490970..9276a49 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 $m \times m \times m$ sized cells and construct the representation based on such structure. It does reduce the memory load by $m^3$ times. Also such
cells cell can act like a building block to construct arbitrary shape and sized 3D regions.