Share Email Print

Proceedings Paper

Adaptive correlation-based tracking algorithm
Author(s): Mark W. Eklund; Mohan M. Trivedi
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The tracking algorithm introduced in this paper was designed with the intent of operation on a pipeline processor. This is different from other algorithms that rely on the branching capabilities which can easily be accomplished by a conventional processor but not pipeline processors. The localization of an object from one frame and the following frame is done using correlation which a pipeline processor handles very well. Finally, little prior knowledge of the object being tracked is required. The heart of this algorithm is the correlation mask. The mask used is a balance between the popular normalized cross correlation filter and the MACE filter. The masks are created from the actual image. Since the object is not a static object, the masks are updated while the object is being tracked. This paper discusses the implementation of this algorithm and its testing.

Paper Details

Date Published: 29 July 1994
PDF: 10 pages
Proc. SPIE 2234, Automatic Object Recognition IV, (29 July 1994); doi: 10.1117/12.181035
Show Author Affiliations
Mark W. Eklund, Univ. of Tennessee/Knoxville (United States)
Mohan M. Trivedi, Univ. of Tennessee/Knoxville (United States)

Published in SPIE Proceedings Vol. 2234:
Automatic Object Recognition IV
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top