📄 http:^^www.cs.rochester.edu^u^dana^
字号:
Date: Thursday, 21-Nov-96 21:02:07 GMTServer: NCSA/1.3MIME-version: 1.0Content-type: text/htmlLast-modified: Monday, 09-Sep-96 18:03:44 GMTContent-length: 3533<HTML><HEAD><TITLE>Dana H. Ballard's Home Page</TITLE></HEAD><BODY><!WA0><IMG ALIGN=TOP SRC="http://www.cs.rochester.edu/images/urcslogo.gif"><!WA1><IMG ALIGN=TOP SRC="http://www.cs.rochester.edu/u/dana/dana.gif"><P><H1>Dana H. Ballard, URCS Faculty Member</H1><P>b. 1946. Ph.D. (1974) University of California at Irvine. VisitingConsultant, Laboratorio Technol. Biomediche, Rome, Italy (74-75).Assistant Professor of Computer Science and Radiology (75-82),Associate Professor of Computer Science (82-87), Professor(87-present); University of Rochester. Co-author of Computer Vision(82). Author of <!WA2><A HREF = "http://www.cs.rochester.edu/u/dana/syllabus.html">Introduction to Natural Computation (Due 97)</A><P>Dana Ballard's main research interest is in computational theories ofthe brain with emphasis on human vision. In 1985 withChris Brown, he led a team that designed and built a high speedbinocular camera control system that is capable of simulating humaneye movements. The system is mounted on a robotic arm that allows itto move at one meter per second in a two meter radius workspace.<P>This system has led to an increased understanding of the role ofbehavior in vision. The theoretical aspects of that system weresummarized in a paper ``Animate Vision,'' which received the BestPaper Award at the 1989 International Joint Conference on ArtificialIntelligence.<P>Dana is also interested in models of the brain that relate to detailedneural models. With <!WA3><A HREF = "http://www.cs.rochester.edu/u/rao"> Raj Rao</A>, Virginia DeSa, Steve Whitehead and Andrew McCallum, he has beeninvestigating the role of reinforcement learning in the learning ofsimple tasks such as Block Stacking. The solutions that can be learnedare suboptimal but extend to complex environments that cannot behandled by traditional approaches. This work has been the basis forthe study of human eye and hand movements using virtual environments.Other research is directed towards learning more general visuo-motorbehaviors. Lambert Wixson and Polly Pook have combined the visionsystem with the Department's Utah dextrous hand. Virginia deSa hasstudied temporally correlated visuo-motor signals using neuralnetwork models.<P><H2>Relevant Publications</H2><UL><LI> Ballard, D. H. ``Reference Frames for Animate Vision.'' Best Paper prize, in Proc., Int'l. Joint Conf. on Artificial Intelligence, August 1989; Proc., 2nd Int'l. Congress of Neuroethology, September 1989. <LI> Ballard, D. H. ``Animate Vision.'' Artificial Intelligence J. 48, 57-86, 1991. <LI> Ballard, D. H., M. M. Hayhoe, F. Li, and S. D. Whitehead. ``Hand-Eye Co-ordination during Sequential Tasks.'' In Proc., Royal Society of London B, London, March 1992. <LI> Pook, P. K. and D. H. Ballard. ``Recognizing Teleoperated Manipulations.'' In Proc., IEEE Int'l. Conf. on Robotics and Automation, May 1993. <LI> Swain, M. J. and D. H. Ballard. ``Color Indexing.'' Int'l. J. of Computer Vision 7 (Special Issue), 1, 11-32, 1991.<LI> Whitehead, S. D. and D. H. Ballard. ``Learning to Perceive and Act.'' Machine Learning 7, 1, 45-83, 1991.<LI> Wixson, L. E. and D. H. Ballard. ``Exploiting World Structure to Efficiently Search for Objects.'' (Special Issue on Active Vision), to appear. </UL><H2>Courses<H2><UL><LI> Computer Science <!WA4><A HREF="http://www.cs.rochester.edu/users/faculty/dana/outline.html"> 240 </A></UL><P><!WA5><A HREF="http://www.cs.rochester.edu/users/faculty.html"> <!WA6><IMG ALIGN=TOP SRC="http://www.cs.rochester.edu/images/up.gif">Back to URCS Faculty directory</A><P><!WA7><A HREF="http://www.cs.rochester.edu/urcs.html"> <!WA8><IMG ALIGN=TOP SRC="http://www.cs.rochester.edu/images/home.gif">Back to URCS Home Page</A><P></BODY></HTML>⌨️ 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 + -