Prepase for submitting

git-svn-id: http://newslabx.csie.ntu.edu.tw/svn/Ginger@84 5747cdd2-2146-426f-b2b0-0570f90b98ed

trunk/RTCSA_SS/02Background.tex

@@ -9,8 +9,8 @@ we are using in this work.
 
 C. Dong et al.~\cite{ChaoDong16} proposed a deep learning method for single image
 super-resolution (SR). Their method learns how to directly map the low-resolution
-image to high-resolution image. They show that the traditional sparse coding
-based SR methods can be reformulated into a deep convolutional neural network.
+image to high-resolution image. They show that the traditional
+SR methods can be reformulated into a deep convolutional neural network.
 SRCNN consists three operations.
 The first layer of SRCNN model extracts the patches from low-resolution image.
 The second layer maps the patches from low-resolution to high-resolution. The
@@ -27,10 +27,8 @@ patches.
 
 \subsection{Thermal cameras}
 In this work, we use two different resolution thermal cameras to play the role
-of low-resolution and high-resolution cameras. For low-resolution camera, we use
-Grid-EYE thermal camera. Grid-EYE is a thermal camera that can output
-$8 \times 8$ 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
+of low-resolution and high-resolution cameras. We use
+Grid-EYE thermal camera.and Lepton 3 as our two different inputs. The
 specification of them are shown in Table~\ref{table:specificationofdevices}.
 
 
@@ -53,10 +51,9 @@ specification of them are shown in Table~\ref{table:specificationofdevices}.
     \hline
     Bits per pixel & 12 & 14\\
     \hline
-    Data Rate & 7.68 kbps & 2.34 mbps\\
-    \hline
   \end{tabular}
-  \caption{Specification of Grid-EYE~\cite{grideye_datasheet} and Lepton 3~\cite{lepton_datasheet}.}
+  \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}
 

trunk/RTCSA_SS/03Design.tex

@@ -58,8 +58,8 @@ lower bound, and regrad it as the trend of the pose changing. Figure~\ref{fig:tr
 shows the filitered data and these lines.
 
 We divide every data into 10 second time windows. If the middle line of the time window
-is at the top one fifth, or the trend is going up, it is a lay on back. If it is at the
-bottom one fifth, or the trend is going down, it is a lay on side. If there are three
+is at the top one fifth, or the trend is going up, it is a lay on back.
+Otherwise, it is a lay on side. If there are three
 continuously same poses, and different from the last turning over, it will be count as
 another turning over.
 
@@ -70,7 +70,7 @@ another turning over.
     \caption{Residual heat on bed.}
     \label{fig:residual_heat}
   \endminipage
-  \minipage{0.6\columnwidth}
+  \minipage{0.55\columnwidth}
     \includegraphics[width=\linewidth]{figures/MinMax_2.pdf}
     \caption{Trend of pose.}
     \label{fig:trend}

trunk/RTCSA_SS/05Conclusion.tex

@@ -2,8 +2,6 @@
 
 In this paper, we propose a data fusing and enhancement method to fuse data from multiple low-resolution
 thermal sensors and use the SRCNN to enhance resolution, the result shows that
-it can improve the accuracy of single frame pose detection by 5\%. 
+it can slightly improve the accuracy of single frame pose detection. 
 We also propose a turning over detection method using multiple frames to reduce the noise
-and considering the trend of pose change to deal with the residual heat. The result shows
-that The accuracy of pose detection is 65\%, and the recall rate and precision of turning over detection
-is 50\% and 83\%.
+and considering the trend of pose change to deal with the residual heat.

trunk/RTCSA_SS/Main.tex

@@ -78,7 +78,7 @@
 %\input{MySetting}
 
 \begin{document}
-\title{Turning Over Detecting Using Low-Resolution Thermal Sensor}
+\title{Turning Over Detecting Using Super-Resolution Thermal Image}
 
 \author{Jyun-Jhe Chou}
 %\author{