📄 http:^^www.cs.columbia.edu^info^research-guide^html^node27.html
字号:
Date: Mon, 25 Nov 1996 20:26:44 GMT
Server: Apache/1.1.1
Content-type: text/html
Content-length: 3793
Last-modified: Fri, 05 Apr 1996 18:20:05 GMT
<!DOCTYPE HTML PUBLIC "-//W3O//DTD W3 HTML 2.0//EN"><!Converted with LaTeX2HTML 95 (Thu Jan 19 1995) by Nikos Drakos (nikos@cbl.leeds.ac.uk), CBLU, University of Leeds ><HEAD><TITLE> John R. Kender</TITLE></HEAD><BODY><meta name="description" value=" John R. Kender"><meta name="keywords" value="main"><meta name="resource-type" value="document"><meta name="distribution" value="global"><P> <BR> <HR><!WA0><A NAME=tex2html390 HREF="http://www.cs.columbia.edu/info/research-guide/html/node28.html"><!WA1><IMG ALIGN=BOTTOM ALT="next" SRC="http://www.cs.columbia.edu/info/research-guide/html/icons//next_motif.gif"></A> <!WA2><A NAME=tex2html388 HREF="http://www.cs.columbia.edu/info/research-guide/html/main.html"><!WA3><IMG ALIGN=BOTTOM ALT="up" SRC="http://www.cs.columbia.edu/info/research-guide/html/icons//up_motif.gif"></A> <!WA4><A NAME=tex2html382 HREF="http://www.cs.columbia.edu/info/research-guide/html/node26.html"><!WA5><IMG ALIGN=BOTTOM ALT="previous" SRC="http://www.cs.columbia.edu/info/research-guide/html/icons//previous_motif.gif"></A> <!WA6><A NAME=tex2html392 HREF="http://www.cs.columbia.edu/info/research-guide/html/node1.html"><!WA7><IMG ALIGN=BOTTOM ALT="contents" SRC="http://www.cs.columbia.edu/info/research-guide/html/icons//contents_motif.gif"></A> <BR><B> Next:</B> <!WA8><A NAME=tex2html391 HREF="http://www.cs.columbia.edu/info/research-guide/html/node28.html"> Shape from Darkness</A><B>Up:</B> <!WA9><A NAME=tex2html389 HREF="http://www.cs.columbia.edu/info/research-guide/html/main.html"> Faculty Research Guide</A><B> Previous:</B> <!WA10><A NAME=tex2html383 HREF="http://www.cs.columbia.edu/info/research-guide/html/node26.html"> Gail E. Kaiser</A><BR> <HR> <P><H1><A NAME=SECTION000120000000000000000> John R. Kender</A></H1><P><H4> Research Area: Computer Vision, Robotic Navigation, Artificial Intelligence</H4><P>My main research interests center around the higher levels ofcomputer visual perception of objects and space. These higher levelsinvolve surfaces, volumes, place locations, topologicalrelationships, and verbal descriptions. This is the mental landscapein which vision meets mainstream AI, and where knowing the "where" ofthings is more important than knowing what the "what" of things are.<P>This research most recently has had four components. The mostclassical component is the development of shape from darkness, a(non-human) method to determining object surface shape from theshadows that the object casts, including shadows that it casts onitself. Less classical are two researches into navigation anddescription. The first of these uses topological relationships ofobjects to describe a navigational path without using metricquantities: this is qualitative direction giving, without the use ofcompass or odometer, much as people do on the back of an envelope.The second explores how the location of a single object in acluttered enviroment can be described purely in spatial terms:medical radiologists do this for a living. The final investigationseeks to develop a Cheshire mouse: an indicating and selecting inputdevice that requires no instrumentation other than the images of themoving and gesturing hand. Like Carrol's Cheshire cat, all thatremains of the standard mouse is the smile (on the hand of the user).<P>We review these four investigations in order, from most classical interms of vision research, to most multidisciplinary. We state whatthe objective of each is, summarize current progress, and sketch oneor two areas of further research that would have the most scientificand engineering payoff.<P><BR> <HR><UL> <LI> <!WA11><A NAME=tex2html393 HREF="http://www.cs.columbia.edu/info/research-guide/html/node28.html#SECTION000121000000000000000"> Shape from Darkness</A><LI> <!WA12><A NAME=tex2html394 HREF="http://www.cs.columbia.edu/info/research-guide/html/node29.html#SECTION000122000000000000000"> Qualitative Navigation</A><LI> <!WA13><A NAME=tex2html395 HREF="http://www.cs.columbia.edu/info/research-guide/html/node30.html#SECTION000123000000000000000"> Natural Language Description from Visual Images</A><LI> <!WA14><A NAME=tex2html396 HREF="http://www.cs.columbia.edu/info/research-guide/html/node31.html#SECTION000124000000000000000"> Visual Interpretation of Gestures</A></UL><BR> <HR><P><ADDRESS><I>Sabah S. al-Binali <BR>Fri Sep 22 16:39:42 EDT 1995</I></ADDRESS></BODY>⌨️ 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 + -