history

来自「VC视频对象的跟踪提取原代码（vc视频监控源码）」· 代码 · 共 79 行

Originally, most of this software was written by Adam Baumberg of the
University of Leeds, UK, using additional libraries not connected with the
University of Leeds.  Later on it was significantly modified by Nils T Siebel
(mainly) at the University of Reading, UK.  A brief history is given below.

The original People Tracker was written by Adam Baumberg at the University of
Leeds in 1993--1995 using C++ running under IRIX on a Silicon Graphics (sgi)
workstation.  It was a research and development system and a proof of concept
for a PhD thesis [1].  The main focus during development was on functionality
and experimental features which represented the state-of-the-art in people
tracking at that time.  A simple process cycle was used for code development.
The only documentation generated was a short programmer's manual (about 5
pages) describing how to write an application using the People Tracker
software.

In 1995--1998 the code was used in a collaboration between the Universities of
Leeds and Reading.  The software was adapted so it could interoperate with a
vehicle tracker which ran on a Sun/Solaris platform [2].  Only little
functionality was changed and added during this time and no new documentation
was created.  Most of the programming on the People Tracker at that time was
done by the original developer, Adam Baumberg.

In 2000, The University of Reading started a major re-design of the code,
adding, removing and significantly changing many files.  The maintenance work
was done within the European research project ADVISOR (IST-1999-11287).  The
team leader was Nils T Siebel.  He did most of the work as well as all
research, algorithms and code (re-)design.  The research aspects are published
within his PhD thesis [3].

With this history, most of these files can now be considered to be originating
from the University of Reading.  For these files the following is valid:

  Main Author: Nils T Siebel of the Computational Vision Group,
               Department of Computer Science, The University of Reading, UK

  Copyright:   (c) 2000--2003 The University of Reading, UK.


The following copyright applies to the original, unchanged files originating
from the University of Leeds:

/*
This source file is the copyright property of the University of Leeds
('The University').

Permission to use, copy, modify, and distribute this source file for
educational, research, and not-for-profit purposes, without fee and
without a signed licensing agreement, is hereby granted, provided that
the above copyright notice, this paragraph and the following three
paragraphs appear in all copies, modifications, and distributions.

In no event shall The University be liable to any party for direct,
indirect, special, incidental or consequential damages, including lost
profits, arising out of the use of this software and its documentation.

The software is provided without warranty. The University has no obligation
to provide maintenance, support, updates, enhancements, or modifications.

This software was written by Adam Baumberg, Vision Group,
School of Computer Studies, University of Leeds, U.K. The code and use
thereof should be attributed to the author where appropriate (including
demonstrations which rely on it's use).
*/

References:

[1] A M Baumberg, Learning Deformable Models for Tracking Human Motion.  PhD
    thesis, School of Computer Studies, University of Leeds, Leeds, UK, October
    1995. 

[2] P Remagnino, A Baumberg, T Grove, T Tan, D Hogg, K Baker and A Worrall.  An
    integrated traffic and pedestrian model-based vision system.  In A Clark,
    editor, Proceedings of the Eighth British Machine Vision Conference
    (BMVC97), pages 380--389. BMVA Press, 1997.

[3] N T Siebel, Design and Implementation of People Tracking Algorithms for
    Visual Surveillance Applications.  PhD thesis, Department of Computer
    Science, The University of Reading, Reading, UK, March 2003.