[an error occurred while processing this directive]
<!-- Page Contents begins Here -->
<!-- ---------------------------------------------------------------- -->
  <style type="text/css">
   .box_rotate {
      -moz-transform: rotate(-90deg);  /* FF3.5+ */
       -o-transform: rotate(-90deg);  /* Opera 10.5 */
  -webkit-transform: rotate(-90deg);  /* Saf3.1+, Chrome */
             filter:  progid:DXImageTransform.Microsoft.BasicImage(rotation=-1.57);  /* IE6,IE7 */
         -ms-filter: "progid:DXImageTransform.Microsoft.BasicImage(rotation=-1.57)"; /* IE8 */   
	 }
  .lagLinePerso {
	font-weight: bold; 
	font-size: 20px; 
	color: #336699; 
	font-family: Arial, Verdana, Helvetica, "Sans Serif"; 
	margin-left: 30px; 
	margin-right: 20px;
	padding-bottom: 0;
	border-bottom: thin solid #FCCE55;
	}
  </style>

<table width="98%">

<td valign=top>
<table cellspacing=0 cellpadding=2 width="150"  bgcolor="#4e7aa6" border=0>
  <tr> 
    <td bgcolor="#4e7aa6" style="  font-weight: bold;color: white">
      Gallery 
    </td>
  </tr>
  <tr> 
    <td bgcolor="#4e7aff" style="  font-weight: bold;color: white">
      Vision 
    </td>
  </tr>

<tr> <td valign=top bgcolor="#c3d1e0" width="98%">
   <center>
    <img src="dame/gallery/moustique.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/pika_track.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/pika.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/robot_track.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/robot_rv.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/part_infra_track.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/part_infra_rv.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/point_track_bear.jpeg" width="150">
      </center>
     </td>
  </tr>
  
    <tr> 
    <td bgcolor="#4e7aff" style="  font-weight: bold;color: white">
      Visual Servoing 
    </td>
  </tr>
  
<tr> <td valign=top bgcolor="#c3d1e0" width="98%">
   <center>
    <img src="dame/gallery/AV_afma6.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/AV_viper.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/AV_illu.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
    <img src="dame/gallery/AV_multi.jpeg" width="150">
    <table height="5"><tr><br> </tr>  </table>
     </center>
     </td>
  </tr>

</table>
</td>

  <td >
      
<h1>Amaury Dame</h1>
<table width="98%"><tr><td width="100%" valign="top">

<p><center>  | <a href="#contact"> Contact </a>
 | <a href="#cursus"> Background and position </a>
 | <a href="#research"> Research </a> 
 | <a href="#publi"> Publications</a> 
 | <a href="#teaching"> Teaching</a> 
 |<a href="#CV"> CV</a> | </center>


<table width="98%"><tr><td width="100%">

<a name="contact"></a>
<h2> New contact </h2>
<p>

  
Amaury Dame is now  "Research Assistant" in the Active Vision Group,
Department of Engineering Science, University of Oxford
  <p>
  
<b>Email :</b>  adame@robots.ox.ac.uk <br>
<b>Web: </b><a      href="http://www.robots.ox.ac.uk/~adame/">Homepage</a>

</p>
</td><td>
<img src="Amaury.Dame.jpg" width="120" border="0" alt="photo">
</td></tr>
</table>

<!-- ---------------------------------------------------------------------->

<a name="cursus"></a>
<h2>Background and Position </h2>

<table>
 <tbody>
	<td width="80%" valign =top>
			
<p>

In 2007, I received a master degree in industrial computer science and electrical engineering from INSA Rennes (<a
href="http://www.insa-rennes.fr">INSA</a>) and Research Master degree in signal and image processing (<a
href="http://ens.univ-rennes1.fr/master-recherche-sti/">STI</a>) from the University of Rennes 1.
</p>
<p>
In December 2010, I received the Ph.D degree in computer science from the University of Rennes after having work 
three years in the Lagadic research team in IRISA/INRIA Rennes Bretagne Atlantique under the supervision of Eric Marchand. The subject of my researches was to develop robust tracking and visual servoing algorithms. 
</p>
<p>
I am currently searching for a postdoctoral position. My research interests include computer vision, active vision and visual servoing.
</p>
<!-- ---------------------------------------------------------------------->
	</td>
	<td width = "40%">
	</td>
</tbody>
</table>
 

<a name="research"></a>
<h2>Research areas </h2>
			
<p>
	  </p>

<p>
<table>
 <tbody>
	<td width="80%" valign =top>
	  <p>
	In this thesis, we focused on both the use of optimization methods and robust alignement function to
	propose new algorithms for the tracking and the visual servoing problems. 
	A  metric derived from information theory, mutual information (MI), is principaly
	considered.  Mutual information is widely used in multi-modal image
	registration (medical applications) since it is robust to
	changes in the lighting conditions and to a wide class of non-linear
	image transformation. 
	</p>
	</td>
</tbody>
</table>
	</p>  
	
<div class="lagLinePerso"> </div>

<h3>Mutual information based tracking</h3> 
<p>

<table>
 <tbody>
	<td width="45%" valign =top>
	<h4>Principle</h4>
	  <p>
	   This work is mixing both information theory and differential tracking to propose
	   a robust and accurate tracker. Mutual information has already been used in several
	   tracking algorithm. In this work we propose a new approach that largely increases its 
	   robustness and accuracy. A new approach is also proposed to perform real-time tracking.
	  </p>

	<h4>Validation</h4>
	  <p>
	  The validity of the approach has been validated through several experiments.
	  The tracker has been evaluated on the metaio benchmark and gives very good results (details to appear).
	  Many sequences have also been treated and shows the accuracy of the tracker as it is show in the video opposite.
	  Since the estimation of the displacement is very accurate, the use of the proposed approach gives a new 
	  solution to augmented reality applications.
	  </p>
	  <p>
	  <small> 
	  <a href=" http://www.irisa.fr/lagadic/pdf/2010_ismar_dame.pdf" >IEEE ISMAR'10<img src="../icones/pdf.gif" align=top border=0 alt =""></a> Best Paper Runner-Up Award  <br>
	  <a href="http://www.irisa.fr/lagadic/pdf/2010_rfia_dame.pdf" >IEEE RFIA'10 <img src="../icones/pdf.gif" align=top border=0 alt =""></a> 
	  </small>
	  </p>


	</td>
	<td width = "2%">
	</td>
	<td width = "30%">
	<center>
	    <h4>Tracking through various appearance variations</h4>
	    <object> <param name="movie" value="http://www.youtube.com/v/9r1KtCq-ABc">  </param>
	    <param name="wmode" value="transparent"> </param>
	    <embed src="http://www.youtube.com/v/9r1KtCq-ABc"  type="application/x-shockwave-flash" wmode="transparent"  width="250" height="210"> </embed>
	      </object><br>
	    <a href="dame/tracking/robot_track.mp4">
	  <!--   <img src="dame/tracking/robot_track.jpeg" alt="photo" border="0" width="200" alt="Tracking using MI"> -->
	  download mp4 here
	  </a>	
	    <h4>Mutlimodal<br> tracking</h4>
	    <object> <param name="movie" value="http://www.youtube.com/v/UFN8C9gzNjA">  </param>
	    <param name="wmode" value="transparent"> </param>
	    <embed src="http://www.youtube.com/v/UFN8C9gzNjA"  type="application/x-shockwave-flash" wmode="transparent"  width="250" height="210"> </embed>
	      </object><br>
	    <a href="dame/tracking/Multimodal_Cesson_Template.mpg">
	  <!--   <img src="dame/tracking/robot_track.jpeg" alt="photo" border="0" width="200" alt="Tracking using MI"> -->
	  download mp4 here
	  </a>	
	</center>
	</td>
	<td width = "30%">
	<center>
	   <h4> Augmented reality <br>application</h4>
	    <object> <param name="movie" value="http://www.youtube.com/v/EEEAEBTc8co">  </param>
	    <param name="wmode" value="transparent"> </param>
	    <embed src="http://www.youtube.com/v/EEEAEBTc8co"  type="application/x-shockwave-flash" wmode="transparent"  width="250" height="210"> </embed>
	      </object><br>
	    <a href="dame/tracking/robot_ra.mpg">
	  <!--   <img src="dame/tracking/robot_rv.jpeg" alt="photo" border="0" width="200" alt="AR using MI"> -->
	  download mp4 here
	  </a>	
	   <h4> Augmented reality <br>application</h4>
	    <object> <param name="movie" value="http://www.youtube.com/v/HA-ESYl9_p4">  </param>
	    <param name="wmode" value="transparent"> </param>
	    <embed src="http://www.youtube.com/v/HA-ESYl9_p4"  type="application/x-shockwave-flash" wmode="transparent"  width="250" height="210"> </embed>
	      </object><br>
	    <a href="dame/tracking/Multimodal_Cesson_AR.mpg">
	  <!--   <img src="dame/tracking/robot_rv.jpeg" alt="photo" border="0" width="200" alt="AR using MI"> -->
	  download mp4 here
	  </a>	
	</center>
	</td>

 </tbody>
</table>



	
<!-- ---------------------------------------------------------------------->
<div class="lagLinePerso"> </div>

<h3>Mutual information based visual servoing</h3> 
<p>

<table>
 <tbody>
	<td width="45%" valign =top>
<h4>Principle </h4> 
	  <p>
	    We propose a new way to achieve visual servoing using
	    directly the information (as defined by Shannon) contained in the images. 
	    In this work mutual-information is used as a
	    new visual feature for visual servoing and allows us to build a new
	    control law to control the 6 dof of the robot. Among
	    various advantages, this approach does not require any matching nor
	    tracking step, is robust to large illumination variation and allows
	    to consider, within the same task, different image modalities.
	  </p>

<h4>Validation </h4> 
	  <p>
	  Several platforms are available to perform the validation of our approaches.
	  The MI-VS has been tested on a 6 dof gantry robot. The algorithm is converging
	  with a 3D trajectory close to the geodesic and a final positioning error of about 0.1 mm in translation and 
	  0.1 ° in rotation with a distance of 1 meter between the camera and the scene.
	  Two typical experiments are presented opposite. The ICRA video 
	  that shows the robustness of the approach with respect to illumination variations
	  and mutlimodality are available <a href="../mpg/2009-dame-icra.avi">here</a>.
	  </p>
	  <p>
	  <small> 
	  <a href="http://www.irisa.fr/lagadic/pdf/2010_icra_dame.pdf" >IEEE ICRA'10 <img src="../icones/pdf.gif" align=top border=0 alt =""></a> <br>
	  <a href="http://www.irisa.fr/lagadic/pdf/2010_rfia_dame.pdf" >IEEE RFIA'10 <img src="../icones/pdf.gif" align=top border=0 alt =""></a> <br>
	  <a href="http://www.irisa.fr/lagadic/pdf/2009_icra_dame.pdf" >IEEE ICRA'09 <img src="../icones/pdf.gif" align=top border=0 alt =""></a> 
	  </small>
	  </p>


	</td>
	<td width = "2%">
	</td>
	<td width = "30%">
	<center>
	    <h4>Mutual information based Visual Servoing</h4>
	   <object> <param name="movie" value="http://www.youtube.com/v/rzNEAqyjos0">  </param>
	    <param name="wmode" value="transparent"> </param>
	    <embed src="http://www.youtube.com/v/rzNEAqyjos0"  type="application/x-shockwave-flash" wmode="transparent"  width="250" height="210"> </embed>
	      </object><br>
	    <a href="dame/Nominal.mpeg">
	  <!--   <img src="dame/Nominal.jpeg" alt="photo" border="0" width="200" alt="Typical positioning task using entropy based visual servoing"> -->
	  download mp4 here
	  </a>	
	</center>
	</td>
	<td width = "30%">
	<center>
	   <h4> Grasping using entropy based visual servoing</h4>
	   <object> <param name="movie" value="http://www.youtube.com/v/3nPmOFYekI0">  </param>
	    <param name="wmode" value="transparent"> </param>
	    <embed src="http://www.youtube.com/v/3nPmOFYekI0"  type="application/x-shockwave-flash" wmode="transparent"  width="250" height="210"> </embed>
	      </object><br>
	    <a href="dame/Nominal.mpeg">
	    <!--   <img src="dame/Grasping.jpeg" alt="photo" border="0" width="200" alt="Grasping using entropy based visual servoing">-->	
	  download mp4 here
	  </a>	
	</center>
	</td>
  </tbody>
</table>

	
</p>

</p>

<!-- ---------------------------------------------------------------------->
<div class="lagLinePerso"> </div>

<h3>Optimal detection and tracking of feature points using Mutual Information</h3> 
<p>

<table>
 <tbody>
	<td width="45%" valign =top>
<h4>Principle </h4> 
	  <p>
	    We propose a new way to achieve feature points detection and tracking.
	    An approach based on Mutual Information is propose to track each point 
	    with a strong robustness to illumination variations. 
	    Considering this tracking approach, an optimal detection of the points 
	    is proposed to choose the points that will be the more efficiently tracked.
	  </p>

<h4>Validation </h4> 
	  <p>
	  The proposed approach has been tested on various image sequences and compared 
	  to the classical KLT approach. As the images opposite shows the proposed algorithm
	  is far more robust to illumination variations.
	  </p>
	  <p>
	  <small> 
	  <a href="http://www.irisa.fr/lagadic/pdf/2009_icip_dame.pdf"> IEEE ICIP'09 <img src="../icones/pdf.gif" align=top border=0 alt =""></a> 
	  </small>
	  </p>


	</td>
	<td width = "20%">
	</td>
	<td width = "40%">


  
	<center>
	<table>
	  <tbody>
		<tr>
		  <td width="6%" valign =top>
		  </td>
		  <td width="52%" valign =top align="center"> <h4>KLT</h4>
		  </td>
		  <td width="52%" valign =top>  <h4>Proposed</h4>
		  </td>
		</tr>

		<tr>
		  <td width="6%" valign =bottom><h5><div class="box_rotate">Nominal conditions</div></h5>
		  </td>
		  <td width="52%" valign =top align="center"> 
		    <img src="dame/point_track/SSDfluxnoillu.jpeg" alt="photo" border="0" width="140" alt="SSD tracking with no illumination variations">
		  </td>
		  <td width="52%" valign =top align="center">  
		    <img src="dame/point_track/MIfluxnoillu.jpeg" alt="photo" border="0" width="140" alt="MI tracking with no illumination variations">
		  </td>
		</tr>

		<tr>
		  <td width="6%" valign =bottom><h5><div class="box_rotate">Global illumination variation</div></h5>
		  </td>
		  <td width="52%" valign =top align="center"> 
		    <img src="dame/point_track/SSDfluxillu.jpeg" alt="photo" border="0" width="140" alt="SSD tracking with  illumination variations">
		  </td>
		  <td width="52%" valign =top align="center">  
		    <img src="dame/point_track/MIfluxillu.jpeg" alt="photo" border="0" width="140" alt="MI tracking with illumination variations">
		  </td>
		</tr>

	    </tbody>
	  </table>
	</center>

	
	</td>
  </tbody>
</table>

	
</p>

</p>

<!-- ---------------------------------------------------------------------->

<a name="publi"></a>
<h2>Publications </h2>

<p>
<a href="../publi/author/Amaury.Dame-eng.html"> Complete list (with postscript or pdf files if available)</a>
<p>

<a name="teaching"></a>
<h2> Teaching </h2>

<p>
Computer vision courses at INSA (National Institute of Applied Sciences) Rennes.
</p>


<!-- ---------------------------------------------------------------------->

<a name="CV"></a>
<h2>Curriculum vitae </h2>

<p>
<a href="dame/cv_english.pdf"> Click here to get a pdf version</a>
<p>

		
	
<!-- ---------------------------------------------------------------- -->
<!-- Page Contents ends Here -->
[an error occurred while processing this directive]