summaryrefslogtreecommitdiffstats
path: root/algorithm.tex
diff options
context:
space:
mode:
authorThibaut Horel <thibaut.horel@gmail.com>2012-09-16 16:50:34 -0700
committerThibaut Horel <thibaut.horel@gmail.com>2012-09-16 16:50:34 -0700
commit0055932482314ec42fb7a090aa72ce1ad79e30b2 (patch)
tree6041e8549358ee189be59830525c4e9195969d37 /algorithm.tex
parente356019058a3bffa7f6ad99f286e22e8d2dbc2d3 (diff)
downloadkinect-0055932482314ec42fb7a090aa72ce1ad79e30b2.tar.gz
Figure placement.
Apparently, this is a well know problem in LaTeX: when you have floats spanning two columns to be placed at the top of the page, you need to place them on the previous page. This is kind of retarded.
Diffstat (limited to 'algorithm.tex')
-rw-r--r--algorithm.tex15
1 files changed, 8 insertions, 7 deletions
diff --git a/algorithm.tex b/algorithm.tex
index 229f605..7f6543a 100644
--- a/algorithm.tex
+++ b/algorithm.tex
@@ -1,4 +1,5 @@
\section{Algorithms}
+
\label{sec:algorithms}
In Section~\ref{sec:uniqueness}, we showed that a nearest-neighbor classifier
@@ -66,13 +67,13 @@ classifier. In general, the higher the threshold $\delta$, the lower the recall
and the higher the precision.
\begin{figure*}[t]
- \centering
- \includegraphics[width=0.99\textwidth]{graphics/limbs.pdf}
- \caption{Histograms of differences between 9 skeleton measurements
- $x_k$ (Section~\ref{sec:experiment}) and their expectation given the
- class $y$. In red, the p.d.f. of a normal distribution with mean and
- variance equal to the empirical mean and variance of the measurement}
- \label{fig:error marginals}
+ \begin{center}
+ \includegraphics[width=0.99\textwidth]{graphics/hallway.png}
+ \end{center}
+ \vspace{-\baselineskip}
+ \caption{Experiment setting. Color image, depth image, and fitted
+ skeleton as captured by the Kinect in a single frame}
+ \label{fig:hallway}
\end{figure*}
\subsection{Sequential hypothesis testing}