diff --git a/trunk/RTCSA_SS/01Introduction.tex b/trunk/RTCSA_SS/01Introduction.tex index 5e8f8ff..d0fd30d 100644 --- a/trunk/RTCSA_SS/01Introduction.tex +++ b/trunk/RTCSA_SS/01Introduction.tex @@ -16,6 +16,6 @@ Super-resolution techniques we can improve the accuracy of turn over detection by XX\%. -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, challenges, 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 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. \ No newline at end of file diff --git a/trunk/RTCSA_SS/02Background.tex b/trunk/RTCSA_SS/02Background.tex index 840f207..d4f943b 100644 --- a/trunk/RTCSA_SS/02Background.tex +++ b/trunk/RTCSA_SS/02Background.tex @@ -1,9 +1,91 @@ \section{Background and Related Works} \label{sec:bk_related} -\subsection{Related 1} -Related 1 +This section describes background of Super-resolution technique, and the sensors +we are using in this work. The related works describes the works that using +thermal image to recognize activity. -\subsection{Related 2} +\subsection{Background} +\paragraph{Super-Resolution Convolutional Neural Network} -Related 2 \ No newline at end of file +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. +SRCNN consists three operations, illustrated in Figure~\ref{fig:SRCNN_model}. +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 +third layer will reconstruct the high-resolution image by the high-resolution +patches. + +\begin{figure}[htb] + \begin{center} + \includegraphics[width=1\linewidth]{figures/SRCNN_model.pdf} + \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 +$8 \times 8$ 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 +specification of them are shown in Table~\ref{table:specification of devices}. + +\begin{table}[hb] + \centering + \footnotesize + \begin{tabular}{|p{3cm}<{\centering}|p{2cm}<{\centering}|p{2.5cm}<{\centering}|} + \hline + Specification & Grid-EYE & Lepton 3\\ + \hline + Resolution & 64 pixels (8x8) & 120x160\\ + \hline + FOV-horizontal & $60^{\circ}$ & $49.5^{\circ}$\\ + \hline + FOV-vertical & $60^{\circ}$ & $61.8^{\circ}$\\ + \hline + Frame rate & 10Hz & 8.7Hz\\ + \hline + Detect temperature range & $-20^{\circ}$C to $80^{\circ}$C & $0^{\circ}$C to $120^{\circ}$C\\ + \hline + Output format & Absolute temperature (Celsius) & 14-bits value which is relative to camera temperature\\ + \hline + Temperature accuracy & $\pm2.5^{\circ}$C & -\\ + \hline + Temperature resolution & $0.25^{\circ}$C & -\\ + \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}.} + \label{table:specification of devices} +\end{table} + +\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} +% \includegraphics[width=0.7\linewidth]{figures/color_guided_SR.pdf} +% \caption{Flow chart of IR-Color multi-sensor imaging system.} +% \label{fig:color_guided_SR} +% \end{center} +% \end{figure} + +F. Almsari et al.~\cite{8713356} applied Generative Adversarial Network (GAN) to the super-resoltuion problem called {\it TIGAN}. TIGAN consists of two networks, generator and discriminator, which learn from each other with zero-sum games and try to find an equilibrium state. The generator was trained to transfer low-resolution thermal image into super-resolution thermal image domain. The generated image should be similar to its ground truth high-resolution image domain. While the discriminator was trained to discriminate between generated image and ground truth high-resolution image. Compared to SRCNN model, it preserves the high-frequency details and gave shaper textures. + +% \begin{figure}[hb] +% \begin{center} +% \includegraphics[width=0.7\linewidth]{figures/GAN_SR.pdf} +% \caption{Network architecture of TIGAN.} +% \label{fig:GAN_SR} +% \end{center} +% \end{figure} +% % background + +The assumption on the resolution of thermal images in above works is at least $120 \times 160$. Compared to the $8 \times 8$ 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. \ No newline at end of file diff --git a/trunk/RTCSA_SS/03Design.tex b/trunk/RTCSA_SS/03Design.tex index b6fd599..c2466b4 100644 --- a/trunk/RTCSA_SS/03Design.tex +++ b/trunk/RTCSA_SS/03Design.tex @@ -1,8 +1,30 @@ \section{Method name} \label{sec:design} -Design +\subsection{System Architecture} +We designed a thermal-box to collect the data. It has four Grideye sensors on the +corners of a 10 cm square and a Lepton 3 at the central. Our method is made by +three parts. The first part is to train the SRCNN model with fused Grideye image +as low-resolution and downscaled Lepton 3 image. The second part, we use the +Super-resolution image to train a neural network model to recognize current pose +is lay on back or lay on side. The third part, because of noise and the residual +heat on bed after turn over, it is difficult to figure out the current pose. We +remove the noise by median filter, and determine the current pose according to +the trend of the possibility from recognition network. -\subsection{Algorithm name} +\subsection{Grideye Data Fusion} + +On the thermal-box, there are four Grideye sensors. At the beginning, we let +the thermal-box faces to an empty bed and records the background temperature. +All the following frames will subtract this background temperature. After that, +we resize four $8 \times 8$ Grideye images to $64 \times 64$ by bilinear +interpolation and than merge them dependence on the distance between thermal-box and +bed, width of sensor square and the FOV of Grideye sensor. + +\begin{enumerate} +\item $D_b$ is the distance between bed and thermal-box. +\item $D_s$ is the width of sensor square also the distance between adjacent sensors. +\item $F$ is the FOV of Grideye sensor which is about 60 degree. +\item $Overlap = 64 - 64 \times (\frac{D_s}{2 \times D_b \times tan(\feac{F}{2})})$ +\end{enumerate} -Algorithm \ No newline at end of file diff --git a/trunk/RTCSA_SS/bibliography.bib b/trunk/RTCSA_SS/bibliography.bib index bcb783e..8c06b8e 100644 --- a/trunk/RTCSA_SS/bibliography.bib +++ b/trunk/RTCSA_SS/bibliography.bib @@ -8,4 +8,16 @@ Cyber-Physical Systems}, month = {September}, address = {Taipei, Taiwan}, publisher = {IEEE Xplore} -} \ No newline at end of file +} +@ARTICLE{ChaoDong16, + author={C. {Dong} and C. C. {Loy} and K. {He} and X. {Tang}}, + journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, + title={Image Super-Resolution Using Deep Convolutional Networks}, + year={2016}, + volume={38}, + number={2}, + pages={295-307}, + keywords={convolution;image resolution;image restoration;learning (artificial intelligence);neural nets;image super-resolution;deep learning method;end-to-end mapping;CNN;low-resolution image;color channel;deep convolutional neural network;reconstruction quality;sparse-coding;image restoration;Image resolution;Neural networks;Image reconstruction;Convolutional codes;Feature extraction;Training;Super-resolution;deep convolutional neural networks;sparse coding;Super-resolution;deep convolutional neural networks;sparse coding}, + doi={10.1109/TPAMI.2015.2439281}, + ISSN={0162-8828}, + month={Feb},} \ No newline at end of file diff --git a/trunk/RTCSA_SS/figures/SRCNN_model.pdf b/trunk/RTCSA_SS/figures/SRCNN_model.pdf new file mode 100644 index 0000000..7e667e1 Binary files /dev/null and b/trunk/RTCSA_SS/figures/SRCNN_model.pdf differ