Share Email Print

Proceedings Paper

Approximation-based video tracking system
Author(s): Keqiang Deng; Joseph N. Wilson
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper describes a two-dimensional target tracking system model and the image algebra specification of its algorithm. The visual tracking process in this model is divided into four subprocesses. Each target is abstracted as a parametrically described closed curve and the neighboring points of the curve. A description of the two-space motion of a target is obtained from the parameters defining the curve in sequential image frames, while curve construction and occlusion detection are accomplished using neighboring points of curve approximations from previous frames. The curve approximation is based on fitting the two-dimensional target boundary contour and is implemented as an error minimization problem. The simplest form of curve considered is an ellipse, but the target descriptions can be made more robust by adding more parameters as needed to describe more complex curves. The parameters of the curves identified in previous frames can be used as constraints in the error minimization process when occlusion is detected. The model can be applied to different types of targets by applying type-specific boundary estimation methods to each target's approximate boundary region. The image algebra description of this algorithm is concise and inherently parallel. This image algebra algorithm specification is of interest because it represents a complex vision activity rather than a simple filtering operation. In particular, the algorithm manipulates many small subimage regions specified by computing their point sets and gives a description of targets as a result, as is typical of vision algorithms. The implementation of the algorithm is described and its performance on a microcomputer vision system is characterized by giving two real-time tracking systems: a two-dimensional block tracking system and one that tracks human faces.

Paper Details

Date Published: 1 July 1991
PDF: 9 pages
Proc. SPIE 1568, Image Algebra and Morphological Image Processing II, (1 July 1991); doi: 10.1117/12.46125
Show Author Affiliations
Keqiang Deng, Univ. of Florida (United States)
Joseph N. Wilson, Univ. of Florida (United States)

Published in SPIE Proceedings Vol. 1568:
Image Algebra and Morphological Image Processing II
Paul D. Gader; Edward R. Dougherty, Editor(s)

© SPIE. Terms of Use
Back to Top