Result Details

Tracking movement objects in sequence pictures

POTÚČEK, I. Tracking movement objects in sequence pictures. ElectronicsLetters.com - http://www.electronicsletters.com, 2003, vol. 2003, no. 2, p. 1-15. ISSN: 1213-161X.
Type
journal article
Language
English
Authors
Potúček Igor, Ing., Ph.D., FIT (FIT)
Abstract

There is presented approach how to tracked tokens in picture sequence.

Keywords

Trajectory Identification, Target Tracking, Kalman Filter, Movement Prediction, Motion Correspondence Problem, Prediction Trees, Backtracking, Continuity, Picture Segmentation.

URL
Annotation

The aim of my work was determine trajectory of moving simple objects - tokens in picture sequence. I used modified Kalman filter to predict and identify the trajectory of moving objects in sequence of 2D image. Presented approach resolves trajectory ambiguities, a case when a number of tokens are large and their speeds and accelerations vary. Correspondence problem is determined between two or more consecutive frames based on tokens similarity. Tracked objects may vanish, appear at a new position and/or mutually occlude each other. Backtracking is used to solve these problems.

Published
2003
Pages
1–15
Journal
ElectronicsLetters.com - http://www.electronicsletters.com, vol. 2003, no. 2, ISSN 1213-161X
BibTeX
@article{BUT41994,
  author="Igor {Potúček}",
  title="Tracking movement objects in sequence pictures",
  journal="ElectronicsLetters.com - http://www.electronicsletters.com",
  year="2003",
  volume="2003",
  number="2",
  pages="1--15",
  issn="1213-161X",
  url="http://www.electronicsletters.com/papers/2003/0002/paper.asp"
}
Projects
Computer graphics algorithms with FPGA support, GACR, Standardní projekty, GA102/02/0507, start: 2002-01-01, end: 2003-12-31, completed
Research groups
Departments
Back to top