📄 http:^^www.cs.wisc.edu^~dyer^dyer.html
字号:
Date: Thu, 07 Nov 1996 19:07:00 GMTServer: NCSA/1.5Content-type: text/htmlLast-modified: Wed, 06 Nov 1996 20:09:05 GMTContent-length: 12835<HTML><HEAD><TITLE>Charles R. Dyer's Home Page</TITLE><LINK REV="made" HREF="mailto:dyer@cs.wisc.edu"></HEAD><BODY background="images/grn2-bak.jpg" bgcolor="#ffffcc" text="000000" link="#0000FF" vlink="#9F5F9F" alink="FF0000"><HR SIZE=5><BR><table border=0 cellspacing=5 cellpadding=10><tr><td><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><!WA0><A HREF="http://www.cs.wisc.edu/~dyer/images/family-interlaced.gif"><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><!WA1><IMG ALIGN=left HSPACE=30 HEIGHT=256 WIDTH=216 SRC="http://www.cs.wisc.edu/~dyer/images/dyer-interlaced.gif"></A></td><td><b><font size=+3>Charles R. Dyer</font></b><br><br>Professor<br><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><!WA2><A HREF="http://www.cs.wisc.edu/">Department of Computer Sciences</A><br><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><!WA3><A HREF="http://wiscinfo.wisc.edu/">University of Wisconsin-Madison</A><br><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><!WA4><A HREF="http://www.mapquest.com/cgi-bin/mqview?screen=wm_search&link=wm_view&uid=c0cacl1060cykpl&name=University@of@Wisconsin&addr=1210@W@Dayton@St&city=Madison&state=WI&zip=53706-1613&level=1&lat=430712&long=-894058&zoom=9">1210 West Dayton Street</A><br><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><!WA5><A HREF="http://www.ci.madison.wi.us/">Madison</A>,<!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><!WA6><A HREF="http://badger.state.wi.us/">Wisconsin</A>53706-1685 USA<br><br>E-mail: <!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><!WA7><A HREF="mailto:dyer@cs.wisc.edu">dyer@cs.wisc.edu</A><br>Telephone: (608) 262-1965<br>Fax: (608) 262-9777<br><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><!WA8><A HREF="http://www.cs.wisc.edu/cgi-bin/finger/m?dyer">Finger info</A><br></tr></table><BR><EM>Ph.D., University of Maryland, 1979</EM>(<!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><!WA9><A HREF="http://www.cs.wisc.edu/~dyer/dyer-cv.ps">Curriculum Vitae</A>)<BR><EM>Areas of Interest:</EM>Computer vision, three-dimensional shape representation,appearance modeling, view synthesis, active vision, visualization<P>Group Leader, <!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><!WA10><A HREF="http://www.cs.wisc.edu/computer-vision/">Wisconsin Computer Vision Group</A><P>Program Co-Chair, <!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><!WA11><A HREF="http://www.cs.wisc.edu/cvpr96">CVPR '96</A><P><HR SIZE=5><H2>Research Interests</H2><H3><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><!WA12><IMG SRC="http://www.cs.wisc.edu/~dyer/images/ball.red.gif"> View Synthesis</H3>The goal of this work is to develop basic tools for controllingin real-time, either autonomously or interactively, a virtual cameraof a real environment. The input is a set of images or videostreams, acquired from fixed or mobile cameras around a site,and the output is a panoramic visualization of the scene in whicha virtual, user-controlled camera can be moved through the environment. With this technology a user could interactively navigate througha real environment, controlling a customized path of views of thesite that are not predetermined by the input images. The main researchquestion is how to adaptively combine a set of basis images to synthesizenew views of the scene without 3D models or 3D scene reconstructionas an intermediate step. Recently we have developed an innovativetechnique, which we call<!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><!WA13><A HREF="http://www.cs.wisc.edu/~seitz/interp/vmorph.html"><I>view morphing</I></A>,that takes two basisimages and interpolates a continuous range of in-between images corresponding to views on the linear path connecting the two camera centers.<P><H3><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><!WA14><IMG SRC="http://www.cs.wisc.edu/~dyer/images/ball.red.gif"> Visual Exploration</H3>Computer vision researchers have recently started to investigate howto actively control the image acquisition process by controllingcamera parameters. We have been studying how to purposefully control theposition and orientation of a camera in order to dynamically adjustviewpoint based on the appearance of a three-dimensional scene. Theuse of real-time viewpoint-control behaviors is important forsolving tasks such as exploring an unknown object in order to findspecific surface markings, building a global model of an unknownshape, or recognizing an object.<P>By coordinating simple observer behaviors that change the appearanceof surfaces in a well-defined way, we simplify the image computationsrequired, make precise the global progress of an algorithm, andeliminate the need for accurate differential measurements of thecamera motion. We believe that this active approach of moving towardsviewpoints that are closely related to the geometry of the viewedobjects is a very important and general one. We have used thisapproach to develop provably-correct algorithms for (1) moving to aside view of a surface of revolution in order to recover its shape, and(2) reconstructing the global surface of an unknown smooth,arbitrarily-shaped object.<P><H3><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><!WA15><IMG SRC="http://www.cs.wisc.edu/~dyer/images/ball.red.gif"> Visualization</H3>In the area of visualization we have developed mapping techniquescapable of generating displays of all possible data objects defined ina user's algorithm, without the need for user-defined, type-specificgraphics display procedures. This capability for displayingarbitrary combinations of an algorithm's data objects in a commonframe of reference, coupled with interactive control of algorithmexecution, provides a powerful way to understand algorithm behavior,especially interactive visual experiments with scientific dataanalysis algorithms. We have implemented a system called VIS-AD forexperimenting with these techniques and have used it for visualizingintermediate and final results of data analysis algorithms forproblems such as discriminating clouds in satellite images.<P><HR SIZE=5><H2>Recent Publications</H2><UL><LI> S. M. Seitz and C. R. Dyer, Cyclic motion analysis using the period trace, in <CITE>Motion-Based Recognition</CITE>, M. Shah and R. Jain, eds., Kluwer, Boston, to appear.<BR><LI> S. M. Seitz and C. R. Dyer, View-invariant analysis of cyclic motion, <CITE>Int. J. Computer Vision</CITE>, to appear.<BR><LI> S. M. Seitz and C. R. Dyer, <!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><!WA16><A HREF="http://www.cs.wisc.edu/~dyer/computer-vision/pubs.html#sigg96-seitz"> View morphing</A>, <CITE>Proc. SIGGRAPH 96</CITE>, 1996, 21-30.<BR><LI> S. M. Seitz and C. R. Dyer, <!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><A HREF="http://www.cs.wisc.edu/~dyer/computer-vision/pubs.html#icpr96-seitz"> Toward image-based scene representation using view morphing</A>, <CITE>Proc. 13th Int. Conf. Pattern Recognition, Vol. I, Track A: Computer Vision</CITE>, 1996, 84-89.<BR><LI> L. Yu and C. R. Dyer, <!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><A HREF="http://www.cs.wisc.edu/~dyer/computer-vision/pubs.html#fest96-yu"> Shape recovery from stationary surface contours by controlled observer motion</A>, in <CITE>Advances in Image Understanding: A Festschrift for Azriel Rosenfeld</CITE>, IEEE Computer Society Press, Los Alamitos, Ca., 1996, 177-193.<BR><LI> K. N. Kutulakos and C. R. Dyer, <!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><A HREF="http://www.cs.wisc.edu/~dyer/computer-vision/pubs.html#cvpr94-2-kutulakos"> Global surface reconstruction by purposive control of observer motion</A>, <CITE>Artificial Intelligence</CITE> <B>78</B>, No. 1-2, 1995, 147-177.<BR><LI> S. M. Seitz and C. R. Dyer, <!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><A HREF="http://www.cs.wisc.edu/~dyer/computer-vision/pubs.html#iccv95-seitz">⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -