TY - JOUR AU - Abdesselam, Salim AU - Baarir, Zine-Eddine PY - 2018 TI - Three variants Particle Swarm Optimization technique for optimal cameras network two dimensions placement JF - Journal of Applied Engineering Science & Technology; Vol 4 No 1 (2018) KW - N2 - 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. UR - https://revues.univ-biskra.dz/index.php/jaest/article/view/3873