Two computer vision-based tracking applications solved using a robust parallel optimizer

Pierre Louis Bazin, Philippe Gérard, André Gagalowicz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A method was developed as a response to the need for a robust optimizer for two different image vision algorithms. Our new approach is a synthesis of two modalities, a simulated annealing technique paired with a parallel search. Using an initial value and the maximum parametric variations, our method searches for a cost function minimum by using parameter subspaces combined with a local simulated annealing algorithm step. The description of our two computer vision applications which relate object tracking to video sequences make it clear why this kind of optimizer was needed. In the cases described, our method provides encouraging results.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Analysis and Processing, ICIAP 1999
Pages526-531
Number of pages6
DOIs
StatePublished - Dec 1 1999
Event10th International Conference on Image Analysis and Processing, ICIAP 1999 - Venice, Italy
Duration: Sep 27 1999Sep 29 1999

Publication series

NameProceedings - International Conference on Image Analysis and Processing, ICIAP 1999

Other

Other10th International Conference on Image Analysis and Processing, ICIAP 1999
CountryItaly
CityVenice
Period9/27/999/29/99

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Two computer vision-based tracking applications solved using a robust parallel optimizer'. Together they form a unique fingerprint.

Cite this