GbLN-PSO and Model-Based Particle Filter Approach for Tracking Human Movements in Large View Cases

Zalili, Musa and Mohd Zuki, Salleh and Rohani, Abu Bakar and Junzo, Watada (2016) GbLN-PSO and Model-Based Particle Filter Approach for Tracking Human Movements in Large View Cases. IEEE Transactions on Circuits and Systems for Video Technology (99). pp. 1-15. ISSN 1051-8215. (Published)

[img] PDF (Journal paper)
stamp.jsp_tp=&arnumber=7108014&tag=1 - Accepted Version
Restricted to Repository staff only

Download (1kB) | Request a copy

Abstract

Camera tracking systems have become a common requirement in today’s society. The availability of high quality and inexpensive video cameras and the increasing need for automated video analysis have generated a great deal of interest in numerous fields. Generally, it is not easy to track human behavior in an environment with a large view. This study aims to address four problems associated with large view in camera tracking system: multiple targets in nonlinear motion, relative size of the targeted object, occlusion and processing time. This paper presents a new method of tracking human movements using a GbLN-PSO and model-based particle filter to address the above problems. The proposed method has been tested with an experimental module using several sets of video data provided by the Eleventh IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS) and two other video streams of UBC hockey and Malaysian football games. The experiment has shown that the accuracy of tracking performance has increased up to 25% compared to others reported work in the scientific literature.

Item Type: Article
Uncontrolled Keywords: GbLN-PSO; Model Based; Multiple Targets; Nonlinear Motion; Particle Filter
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Ms. Zalili Musa
Date Deposited: 20 Apr 2016 06:17
Last Modified: 07 Sep 2018 01:47
URI: http://umpir.ump.edu.my/id/eprint/12725
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item