home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!pipex!bnr.co.uk!uknet!comlab.ox.ac.uk!phst
- From: phst@robots.ox.ac.uk (Phil Torr)
- Newsgroups: sci.math.stat
- Subject: robust estimation
- Summary: Robust estimation in computer vision
- Keywords: Robust, Vision, Regression,
- Message-ID: <1992Dec22.153952.28319@percy.robots.ox.ac.uk>
- Date: 22 Dec 92 15:39:52 GMT
- Organization: Robotics Research Group, Engineering Science Dept, Oxford, UK.
- Lines: 12
- Originator: phst@percy.robots
-
- I am working in the field of computer vision and would like to quiz
- the stats community as regards to solution of the following problem:
-
- I have a set of data in n dimensional space (n=7,8,9) which i know
- is spanned by several hyper-planes (though i do not know the number
- of the hyperplanes i do know that they are of dimensionality n-1)
-
- does anybody know a good way of estimating these different hyperplanes
- given that i do not know which points lie on which hyperplane?
-
-
- thanks in advance Philip Torr
-