Geodesic
Approaches to the optimization and parallelization of computations in the problem of detecting objects of different classes in the image
Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika, no. 2 (2012), pp. 68-82

Voir la notice de l'article provenant de la source Math-Net.Ru

This paper considers the problem of object detection in static images. We describe a state-of-the-art method based on Latent SVM algorithm. A well-known approach to speed up calculations, the construction of cascade classifiers, is used. We describe a computational scheme that uses cascade modification of the original Latent SVM algorithm The issues of parallelization and performance optimization are discussed. We analyze the most timeconsuming parts of implementation, consider several parallelization schemes and aspects of their performance. The results of numerical experiments on PASCAL Visual Object Challenge 2007 image dataset are given.
Keywords: object detection, algorithm Latent SVM, parallelization.
Mots-clés : cascade classifier 
@article{VYURV_2012_2_a6,
     author = {E. A. Kozinov and V. D. Kustikova and I. B. Meyerov and A. N. Polovinkin and A. A. Sidnev},
     title = {Approaches to the optimization and parallelization of computations in the problem of detecting objects of different classes in the image},
     journal = {Vestnik \^U\v{z}no-Uralʹskogo gosudarstvennogo universiteta. Seri\^a Vy\v{c}islitelʹna\^a matematika i informatika},
     pages = {68--82},
     publisher = {mathdoc},
     number = {2},
     year = {2012},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VYURV_2012_2_a6/}
}
TY  - JOUR
AU  - E. A. Kozinov
AU  - V. D. Kustikova
AU  - I. B. Meyerov
AU  - A. N. Polovinkin
AU  - A. A. Sidnev
TI  - Approaches to the optimization and parallelization of computations in the problem of detecting objects of different classes in the image
JO  - Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika
PY  - 2012
SP  - 68
EP  - 82
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VYURV_2012_2_a6/
LA  - ru
ID  - VYURV_2012_2_a6
ER  - 
%0 Journal Article
%A E. A. Kozinov
%A V. D. Kustikova
%A I. B. Meyerov
%A A. N. Polovinkin
%A A. A. Sidnev
%T Approaches to the optimization and parallelization of computations in the problem of detecting objects of different classes in the image
%J Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika
%D 2012
%P 68-82
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VYURV_2012_2_a6/
%G ru
%F VYURV_2012_2_a6
E. A. Kozinov; V. D. Kustikova; I. B. Meyerov; A. N. Polovinkin; A. A. Sidnev. Approaches to the optimization and parallelization of computations in the problem of detecting objects of different classes in the image. Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika, no. 2 (2012), pp. 68-82. http://geodesic.mathdoc.fr/item/VYURV_2012_2_a6/