From 0055932482314ec42fb7a090aa72ce1ad79e30b2 Mon Sep 17 00:00:00 2001 From: Thibaut Horel Date: Sun, 16 Sep 2012 16:50:34 -0700 Subject: 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. --- algorithm.tex | 15 +++++---- experimental.tex | 101 ++++++++++++++++++++++--------------------------------- uniqueness.tex | 10 ++++++ 3 files changed, 58 insertions(+), 68 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} diff --git a/experimental.tex b/experimental.tex index 2c537df..8133ec1 100644 --- a/experimental.tex +++ b/experimental.tex @@ -9,6 +9,31 @@ results. \subsection{Dataset} \label{sec:experiment:dataset} +\begin{figure}[t] + \begin{center} + \includegraphics[width=0.49\textwidth]{graphics/frames.pdf} + \end{center} + \caption{Distribution of the frequency of each individual in the + dataset} + \label{fig:frames} +\end{figure} + +\begin{figure*}[t] +\begin{center} +\subfloat[Mixture of Gaussians]{ + \includegraphics[width=0.49\textwidth]{graphics/offline-nb.pdf} + \label{fig:offline:nb} +} +\subfloat[Sequential Hypothesis Testing]{ + \includegraphics[width=0.49\textwidth]{graphics/offline-sht.pdf} + \label{fig:offline:sht} +} + \caption{Results with 10-fold cross-validation for the top $n_p$ most present people} +\label{fig:offline} +\end{center} +\end{figure*} + + The Kinect outputs three primary signals in real-time: a color image stream, a depth image stream, and microphone output (\fref{fig:hallway}). For our purposes, we focus on the depth image stream. As the Kinect was designed to @@ -49,16 +74,6 @@ with detected figures, and the fitted skeleton of a person in a single frame. Skeletons are fit from roughly 1-5 meters away from the Kinect. For each frame with a skeleton we record the color image and the positions of the joints. -\begin{figure*}[t] - \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*} - For some frames, one or several joints are out of the frame or are occluded by another part of the body. In those cases, the coordinates of these joints are either absent from the frame or present but tagged as \emph{Inferred} by the @@ -66,7 +81,6 @@ Kinect SDK. Inferred means that even though the joint is not visible in the frame, the skeleton-fitting algorithm attempts to guess the right location. Note that in the experiment design we exclude inferred data points. - \subsection{Experiment design} \label{sec:experiment-design} @@ -143,15 +157,6 @@ happens if the noise from the Kinect is reduced. %\end{center} %\end{table} -\begin{figure}[t] - \begin{center} - \includegraphics[width=0.49\textwidth]{graphics/frames.pdf} - \end{center} - \caption{Distribution of the frequency of each individual in the - dataset} - \label{fig:frames} -\end{figure} - \subsection{Offline learning setting} \label{sec:experiment:offline} @@ -189,21 +194,6 @@ we reach 90\% accuracy at 60\% recall for a group size of 10 people. %for the least present people, as seen in \fref{fig:frames}, which does not %permit a proper training of the algorithm. -\begin{figure*}[t] -\begin{center} -\subfloat[Mixture of Gaussians]{ - \includegraphics[width=0.49\textwidth]{graphics/offline-nb.pdf} - \label{fig:offline:nb} -} -\subfloat[Sequential Hypothesis Testing]{ - \includegraphics[width=0.49\textwidth]{graphics/offline-sht.pdf} - \label{fig:offline:sht} -} - \caption{Results with 10-fold cross-validation for the top $n_p$ most present people} -\label{fig:offline} -\end{center} -\end{figure*} - %\begin{figure}[t] % \begin{center} % \includegraphics[width=0.80\textwidth]{graphics/10fold-naive.pdf} @@ -254,7 +244,8 @@ recognition rates mostly above 90\% for group sizes of 3 and 5. the group as in Figure~\ref{fig:offline}} \label{fig:online} \end{figure} -\begin{figure}[t] + +\begin{figure}[t!] \begin{center} \includegraphics[width=0.49\textwidth]{graphics/face.pdf} \end{center} @@ -289,23 +280,6 @@ within 10\% of face recognition at most thresholds. %runs which face recognition and skeleton recognition can classify frames, %which we discuss in the next experiment. - - -\begin{figure}[t] -\begin{center} - \includegraphics[width=0.49\textwidth]{graphics/back.pdf} -\end{center} -\caption{Results with people walking away from and toward the camera} -\label{fig:back} -\end{figure} -\begin{figure}[t] -\begin{center} - \includegraphics[width=0.49\textwidth]{graphics/var.pdf} -\end{center} -\caption{Results with and without halving the variance of the noise} -\label{fig:var} -\end{figure} - \subsection{Walking away} In the next experiment, we include the runs in which people are walking away @@ -331,6 +305,13 @@ they are walking towards the camera. % \label{fig:back} %\end{figure} +\begin{figure}[t] + \centering + \includegraphics[width=0.49\textwidth]{graphics/back.pdf} +\caption{Results with people walking away from and toward the camera} +\label{fig:back} +\end{figure} + \fref{fig:back} compares the results obtained in \xref{sec:experiment:offline} with people walking toward the camera, with the results of the same experiment on the dataset of runs of people walking away from the camera. @@ -373,14 +354,12 @@ a roughly 20\% increase in performace across most thresholds. We believe these results would significantly outperform face recognition in a similar setting. -%\begin{figure}[t] -% \begin{center} -% \includegraphics[width=0.49\textwidth]{graphics/var.pdf} -% \end{center} -% \vspace{-1.5\baselineskip} -% \caption{Results with and without halving the variance of the noise} -% \label{fig:var} -%\end{figure} +\begin{figure}[t] + \centering + \includegraphics[width=0.49\textwidth]{graphics/var.pdf} +\caption{Results with and without halving the variance of the noise} +\label{fig:var} +\end{figure} %%% Local Variables: %%% mode: latex diff --git a/uniqueness.tex b/uniqueness.tex index 429e7de..3c23f7a 100644 --- a/uniqueness.tex +++ b/uniqueness.tex @@ -1,6 +1,16 @@ \section{Skeleton uniqueness} \label{sec:uniqueness} +\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} +\end{figure*} + The most obvious concern raised by trying to use skeleton measurements as a recognizable biometric is their uniqueness. Are skeletons consistently and sufficiently distinct to use them for person recognition? -- cgit v1.2.3-70-g09d2