Three variants Particle Swarm Optimization technique for optimal cameras network two dimensions placement

  • Salim Abdesselam LESIA Laboratory, Department of electrical engineering, Biskra University, P.O.BOX 14 RP, Biskra, Algeria
  • Zine-Eddine Baarir LESIA Laboratory, Department of electrical engineering, Biskra University, P.O.BOX 14 RP, Biskra, Algeria

Abstract

This paper addresses the problem of optimal placement in two-dimensions of the cameras network for the motion capture (MoCap) system. In fact, the MoCap system is a three- dimensional representation environment used mainly to reconstruct a real motion by using a number of fixed cameras (in position and pose). The main objective is to find the optimal placement of all cameras in a minimal time under a major constraint in order to capture each reflector that must be seen by at least three cameras in the same frame in a sequence of a random motion. The two-dimensional representation is only used to solve the problem of reflector recovery. The choice of two-dimensional representation is to reduce the resolution of a three- dimensional recovery problem to a simple two-dimensional recovery, especially if all the cameras have the same height. With this strategy, the placement of cameras network is not treated as an image processing problem. The use of three variants optimization techniques by Particle Swarm Optimization (Standard Particle Swarm Optimization, Weight Particle Swarm Optimization and Canonical Particle Swarm Optimization), allowed us to solve the problem of cameras network placement in a minimal amount of time. The overall recovery objective has been achieved despite the complexity imposed in the third scenario by the Canonical Particle Swarm Optimization variant.

Published
2018-05-24
How to Cite
ABDESSELAM, Salim; BAARIR, Zine-Eddine. Three variants Particle Swarm Optimization technique for optimal cameras network two dimensions placement. Journal of Applied Engineering Science & Technology, [S.l.], v. 4, n. 1, p. 37-45, may 2018. ISSN 2352-9873. Available at: <http://revues.univ-biskra.dz/index.php/jaest/article/view/3873>. Date accessed: 08 dec. 2021.
Section
Section A: Electrical, Electronics and Automatic Engineering

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.