this is for holding javascript data
Volker Strobel edited Another_idea_if_the_homography__.tex
almost 8 years ago
Commit id: 0ec6cd126c056aa537760b73f30684bb1c23b54b
deletions | additions
diff --git a/Another_idea_if_the_homography__.tex b/Another_idea_if_the_homography__.tex
index 9a94b82..1dd83dc 100644
--- a/Another_idea_if_the_homography__.tex
+++ b/Another_idea_if_the_homography__.tex
...
Another idea---if the homography-based approach is used for
labeling---was to use the amount of detected keypoints
($K$) as confidence
value. However, again, no linear
relation relationship between
$K$ and the error in $x-direction$ ($X$) and the
two variables error in $y-direction$ ($Y$)
could be found
(Figure~\ref{fig:cor_sim_confi}).
\begin{figure}[h!]
\begin{center}
\includegraphics[width=0.7\columnwidth]{figures/fig_cor_sift_confi/default_figure}
\caption{{\label{fig:cor_sift_confi} Dependence structure between number of keypoints and quality
of the measurement.%
}}
\end{center}
\end{figure} (Figure~\ref{fig:cor_sim_confi}): $\rho_{K, X} = 0.10$, $\rho_{K, Y} = 0.01$.