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

Pierre Louis Bazin; Philippe Gérard; André Gagalowicz

doi:10.1109/ICIAP.1999.797649

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

Pierre Louis Bazin, Philippe Gérard, André Gagalowicz

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999
Pages	526-531
Number of pages	6
DOIs	https://doi.org/10.1109/ICIAP.1999.797649
State	Published - Dec 1 1999
Event	10th International Conference on Image Analysis and Processing, ICIAP 1999 - Venice, Italy Duration: Sep 27 1999 → Sep 29 1999

Publication series

Name	Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999

Other

Other	10th International Conference on Image Analysis and Processing, ICIAP 1999
Country	Italy
City	Venice
Period	9/27/99 → 9/29/99

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIAP.1999.797649

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

Bazin, P. L., Gérard, P., & Gagalowicz, A. (1999). Two computer vision-based tracking applications solved using a robust parallel optimizer. In Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999 (pp. 526-531). [797649] (Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999). https://doi.org/10.1109/ICIAP.1999.797649

Two computer vision-based tracking applications solved using a robust parallel optimizer. / Bazin, Pierre Louis; Gérard, Philippe; Gagalowicz, André.

Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999. 1999. p. 526-531 797649 (Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Bazin, PL, Gérard, P & Gagalowicz, A 1999, Two computer vision-based tracking applications solved using a robust parallel optimizer. in Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999., 797649, Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999, pp. 526-531, 10th International Conference on Image Analysis and Processing, ICIAP 1999, Venice, Italy, 9/27/99. https://doi.org/10.1109/ICIAP.1999.797649

@inproceedings{02f4a6d767fb47c29779873c29d6b4ea,

title = "Two computer vision-based tracking applications solved using a robust parallel optimizer",

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.",

author = "Bazin, {Pierre Louis} and Philippe G{\'e}rard and Andr{\'e} Gagalowicz",

year = "1999",

month = dec,

day = "1",

doi = "10.1109/ICIAP.1999.797649",

language = "English (US)",

isbn = "0769500404",

series = "Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999",

pages = "526--531",

booktitle = "Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999",

note = "10th International Conference on Image Analysis and Processing, ICIAP 1999 ; Conference date: 27-09-1999 Through 29-09-1999",

}

TY - GEN

T1 - Two computer vision-based tracking applications solved using a robust parallel optimizer

AU - Bazin, Pierre Louis

AU - Gérard, Philippe

AU - Gagalowicz, André

PY - 1999/12/1

Y1 - 1999/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84890415420&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890415420&partnerID=8YFLogxK

U2 - 10.1109/ICIAP.1999.797649

DO - 10.1109/ICIAP.1999.797649

M3 - Conference contribution

AN - SCOPUS:84890415420

SN - 0769500404

SN - 9780769500409

T3 - Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999

SP - 526

EP - 531

BT - Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999

T2 - 10th International Conference on Image Analysis and Processing, ICIAP 1999

Y2 - 27 September 1999 through 29 September 1999

ER -