this is for holding javascript data
Volker Strobel edited DeclareMathOperator_argmin_arg_min_DeclareMathOperator__1.tex
almost 8 years ago
Commit id: c12a1d7d056ba52beca65ea5ea686d0a60584847
deletions | additions
diff --git a/DeclareMathOperator_argmin_arg_min_DeclareMathOperator__1.tex b/DeclareMathOperator_argmin_arg_min_DeclareMathOperator__1.tex
index 0a1df1a..7880302 100644
--- a/DeclareMathOperator_argmin_arg_min_DeclareMathOperator__1.tex
+++ b/DeclareMathOperator_argmin_arg_min_DeclareMathOperator__1.tex
...
In all cases, the result will be a labeled dataset of images and corresponding $x,y$-positions. The $x,y$-positions are of different quality depending on the used technique: orthomap-based, poster-based, or motion tracking-based.
\section{Pillar II: Texton-based Approach}
\label{sec:textons}
In this section, the core of the proposed algorithm, the
implementation of the proposed texton framework is described. The
histograms of textons are used as features for the $k$-Nearest
Neighbors ($k$NN) algorithm. The outputs of this regression technique
are possible $x,y$-coordinates for a given image.
In the following pseudo code, $M$ represents the number of particles,
$z_t^x$ the output of the texton framework at time $t$, and $f_t^x$
the estimated flow at time $t$.
Importantly, for generating the training dataset, no subsampling was
used. Therefore, the training dataset will not show any variance, if
the same images were used.