TY  - CONF
VL  - 9443
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84925433489&doi=10.1117%2f12.2178884&partnerID=40&md5=8c77858f9d90dc4cae8688cef04e63bf
A1  - Saini, S.
A1  - Rambli, D.R.B.A.
A1  - Sulaiman, S.B.
A1  - Zakaria, M.N.B.
A1  - Tomi, A.B.
SN  - 0277786X
PB  - SPIE
Y1  - 2015///
KW  - Extraction; Image processing; Optimization
KW  -  3D tracking; APF; Pose tracking; PSO; Silhouette extraction
KW  -  Particle swarm optimization (PSO)
ID  - scholars6366
TI  - Particle swarm optimization based articulated human pose tracking using enhanced silhouette extraction
N2  - In this paper, we address the problem of three dimensional human pose tracking and estimation using Particle Swarm Optimization (PSO) with an improved silhouette extraction mechanism. In this work, the tracking problem is formulated as a nonlinear function optimization problem so the main objective is to optimize the fitness function between the 3D human model and the image observations. In order to improve the tracking performance, new shadow detection, removal and a level-set mechanism are applied during silhouette extraction. Both the silhouette and edge likelihood are used in the fitness function. Experiments using HumanEva-II dataset demonstrate that the proposed approach performance is considerably better than baseline algorithm which uses the Annealed Particle Filter (APF). © 2015 SPIE.
N1  - cited By 1; Conference of 6th International Conference on Graphic and Image Processing, ICGIP 2014 ; Conference Date: 24 October 2014 Through 26 October 2014; Conference Code:111632
AV  - none
ER  -