Public Web Only Documents from 1998 to Present
(Copyright 2005)
|
The Vision Feature Analysis Tool Component of the iLab
Neuromorphic Vision Toolkit - 2004
|
T. Nathan Mundhenk, |
Chris Landauer, |
Kirstie Bellman |
and |
Laurent Itti |
|
Web Published Document |
|
|
|
University of Southern California |
July |
|
Abstract:
|
The Vision Feature Analysis Tool
(VFAT) is designed to enable quick
analysis of features in an image for the purpose of identification and
tracking. This
document is an overview of the VFAT which is a work in progress. It is
designed to give
the other project authors information they need to integrate or
interoperate with it. As it is
a work in progress specific information about certain aspects may be
lacking but I will
attempt to make some suggestion about the structure of the final
implementation. |
|
|
|
|
|
|
iRoom Expert Module Standard - 2004
|
T. Nathan Mundhenk, |
Chris Landauer |
and |
Kirstie Bellman |
|
Web Published Document |
|
|
|
University of Southern California |
July |
|
Abstract:
|
The iRoom expert module standard
(IEMS) is being developed to accomplish several
objectives. The first and most notable is it should be developed to
allow as effortless as
possible sharing of resources authored by different individuals as part
of the iRoom
development project. Additionally, it should set a standard for
information among experts
that forces the authors of modules to think about the extensibility of
the information
which they can provide. |
|
|
|
|
|
|
iRoom Arch Overview - 2004
|
T. Nathan Mundhenk, |
Chris Landauer |
and |
Kirstie Bellman |
|
Web Published Document |
|
|
|
University of Southern California |
July |
|
|
|
|
|
|
|
A review of work on modular standardization and color
tracking - 2004
|
T. Nathan Mundhenk, |
Chris Landauer |
and |
Kirstie Bellman |
|
Web Published Document |
|
|
|
University of Southern California |
July |
|
Abstract:
|
This document outlines the proposed
iRoom Expert Module Standard (IEMS)
as well as gives a review of a real time color tracker, which will be
used as an initial first
vision tracker in the iRoom. The IEMS standard should help illuminate
how as more
powerful trackers are developed they can be integrated into the iRoom
as easily as
possible. This document contains all new material some of it mostly
technical. The table
of contents is there so that one can skip such sections. The technical
sections are for the
groups benefit. Note: I treated this as an informal write-up. |
|
|
|
|
|
|
Linear dimensionality reduction of motion information -
2004
|
T. Nathan Mundhenk |
and |
Laurent Itti |
|
Web Published Document |
|
|
|
University of Southern California |
November |
|
Abstract:
|
Like many other types of image
information, motion information can be analyzed
at multiple scales and in multiple directions. For instance, it is easy
to imagine motion
information in multiple directions. An object may move left or an
object may move right.
Thus, to catch motion, many filter schemes and biological systems
detect motion in
certain directions (Rall 1970; Prodöhl, Würtz and von
der Malsberg 2003). Motion may
also be detected in the absence of direction but suffers from the
problem that all motion is
treated equally. Thus, detecting motion without direction is no
different than detecting
flicker. Since we need directional information to be informative about
the nature of a
motion being observed we must introduce the first few dimensions of
motion
information, which is the direction of motion. |
|
|
|
|
|
|
The agent I think I am: Modeling symptoms and
observations in schizophrenia as they relate to a sense of agency and
the ability to mirror behavior - 2003
|
T. Nathan Mundhenk |
and |
Michael A. Arbib |
|
Web Published Document |
|
|
|
University of Southern California |
|
|
|
|
|
|
|
|
Knowledge of Agents In Language and Action A model
derived from studies of psychopathology and current models in language
and action - 2002
|
T. Nathan Mundhenk |
and |
Michael A. Arbib |
|
Unpublished internal Document |
|
|
|
University of Southern California |
December |
|
|
|
|
|
|
|