@ -8,14 +8,17 @@ all days.\textcolor{red}{(source?)}. By the low resolution thermal camera, we
can obtain the daily activities informations, but not reveal too much privacy
like the RGB camera.
{\bf Contribution} Contribution
{\bf Contribution}
In this work, we deployed multiple low resolution thermal camera to monitor the
turn over frequency while sleeping. With multiple thermal camera and
Super-resolution techniques we can improve the accuracy of turn over detection
by XX\%.
turn over frequency while sleeping. With multiple thermal camera,
Super-resolution techniques, and our method, we can have 50\% recall rate and 83\% precision
on turning over detection.
The remaining of this paper is organized as follow. Section~\ref{sec:bk_related} presents related works and background for developing the methods. Section~\ref{sec:design} presents the system architecture, and the developed mechanisms. Section~\ref{sec:eval} presents the evaluation results of proposed mechanism and Section~\ref{sec:conclusion} summaries our works.
The remaining of this paper is organized as follow. Section~\ref{sec:bk_related}
presents background for developing the methods. Section~\ref{sec:design} presents
the system architecture, and the developed mechanisms. Section~\ref{sec:eval}
presents the evaluation results of proposed mechanism and Section~\ref{sec:conclusion} summaries our works.
%%\caption{Illustration of super-resolution convolutional neural network (SRCNN) model~\cite{ChaoDong16}.}
%%\label{fig:SRCNN_model}
%%\end{center}
%%\end{figure}
\subsection{Thermal cameras}
In this work, we use two different resolution thermal camera to play the role
of low-resolution and high-resolution camera. For low-resolution camera, we use
Grid-EYE thermal camera. Grid-EYE is a thermal camera that can output
$8\times8$ pixels thermal data with $2.5^\circ C$ accuracy and $0.25^\circ C$
resolution at $10$ fps. For the high-resolution one, we use Lepton 3. The
specification of them are shown in Table~\ref{table:specificationofdevices}.
\begin{table}[hb]
@ -55,19 +62,11 @@ patches.
Data Rate & 7.68 kbps & 2.34 mbps\\
\hline
\end{tabular}
\caption{Specification of Grid-EYE and Lepton 3.}
\caption{Specification of Grid-EYE~\cite{grideye_datasheet} and Lepton 3~\cite{lepton_datasheet}.}
\label{table:specificationofdevices}
\end{table}
\subsection{Thermal cameras}
In this work, we use two different resolution thermal camera to play the role
of low-resolution and high-resolution camera. For low-resolution camera, we use
Grid-EYE thermal camera. Grid-EYE is a thermal camera that can output
$8\times8$ pixels thermal data with $2.5^\circ C$ accuracy and $0.25^\circ C$
resolution at $10$ fps. For the high-resolution one, we use Lepton 3. The
specification of them are shown in Table~\ref{table:specificationofdevices}.
\subsection{Related Works}
%\subsection{Related Works}
%X. Chen et al.~\cite{7805509} proposed to use the visible camera as a guidance to super resolution the IR images. They proposed the IR-RBG multi-sensor imaging system. The approach bases on the fact that RGB channels have different correlation with IR images. To avoid wrong texture transfer, the method used cross correlation to find the proper matching between the region of IR image and RGB image. Next, the method applied sub-pixel estimation and guided filtering to remove the noise and discontinuities in IR image. At the last step of the iteration, they used truncated quadric model as the cost function to terminate the algorithm. After the iteration, the method fine tuned the output IR image with outlier detection to remove the black points which only appear at the edge of IR image.
%\begin{figure}[ht]
%\begin{center}
@ -88,4 +87,4 @@ specification of them are shown in Table~\ref{table:specificationofdevices}.
%\end{figure}
%% background
The assumption on the resolution of thermal images in above works is at least $120\times160$. Compared to the $8\times8$ thermal images collected by Grid-EYE sensors, more thermal features are available. In addition, these works use RGB images as reference to train the model. In this work, RGB camera will not be used so as to protect privacy.
%The assumption on the resolution of thermal images in above works is at least $120\times160$. Compared to the $8\times8$ thermal images collected by Grid-EYE sensors, more thermal features are available. In addition, these works use RGB images as reference to train the model. In this work, RGB camera will not be used so as to protect privacy.
Hobe
5 years ago