DocumentCode :
2530616
Title :
A Metaheuristic Bat-Inspired Algorithm for Full Body Human Pose Estimation
Author :
Akhtar, S. ; Ahmad, A.R. ; Abdel-Rahman, E.M.
Author_Institution :
Syst. Design Eng. Dept., Univ. of Waterloo, Waterloo, ON, Canada
fYear :
2012
fDate :
28-30 May 2012
Firstpage :
369
Lastpage :
375
Abstract :
This paper addresses the problem of full body articulated human motion tracking from multi-view video data recorded in a laboratory environment. The problem is formulated as a high dimensional (31-dimensional) non-linear optimization problem. In recent years, metaheuristics such as Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Artificial Immune System (AIS), Firefly Algorithm (FA) are applied to complex non-linear optimization problems. These population based evolutionary algorithms have diversified search capabilities and are computationally robust and efficient. One such recently proposed metaheuristic, Bat Algorithm (BA), is employed in this work for full human body pose estimation. The performance of BA is compared with Particle Filter (PF), Annealed Particle Filter (APF) and PSO using a standard data set. The qualitative and the quantitative evaluation of the performance of full body human tracking demonstrates that BA performs better then PF, APF and PSO.
Keywords :
nonlinear programming; particle filtering (numerical methods); pose estimation; annealed particle filter; ant colony optimization; artificial immune system; firefly algorithm; full body articulated human motion tracking; full body human pose estimation; high dimensional nonlinear optimization problem; laboratory environment; metaheuristic bat-inspired algorithm; multiview video data; particle swarm optimization; population based evolutionary algorithm; Approximation algorithms; Barium; Cameras; Estimation; Humans; Joints; Optimization; Human pose estimation; articulated human tracking; bat optimization; soft computing; swarm optimization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer and Robot Vision (CRV), 2012 Ninth Conference on
Conference_Location :
Toronto, ON
Print_ISBN :
978-1-4673-1271-4
Type :
conf
DOI :
10.1109/CRV.2012.55
Filename :
6233164
Link To Document :
بازگشت