02802ntm a2200241 a 4500001001400000003000700014005001700021008004100038020002200079040000800101100001600109245008400125260003400209300005800243500005700301502009300358504002900451520189400480610007202374650004502446650001102491856005802502vtls000099676KUKTEM20251117113326.0170502t2016    my da  f am   000 0 eng d  aTHE0001293(Local)  aUMP0 aZalili Musa13aAn enhancement particle-based method for dynamic object tracking /cZalili Musa  aKuantan, Pahang :bUMP,c2016  axvi, 140 p. :bill. (some col.) ;c30 cm. +e1 CD ROM  aFaculty of Computer Systems and Software Engineering  aThesis (Doctor of Philosophy in Computer Science) -- Universiti Malaysia Pahang – 2016  aBibliography : p. 94-1073 aCamera 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 three problems associated with object tracking. The first problem to be considered in this study is to improve the accuracy of object detection for multiple targets in nonlinear motion and during the occlusions occurs. Secondly, to track the precise location of object in relative size. The third problem to be considered is a to improve the processing time for the process of object detection and tracking. Thus, to address the accuracy of object detection, we proposed a new method of dynamic template matching using Global best Local Neighborhood in Particle Swarm Optimization (GbLN-PSO). In this study, feature-based approach using a GbLN-PSO algorithm will be applied to search the minimum value of dynamic template matching process. Furthermore, a model-based particle filter is used to address the problem of tracking objects precisely. This method is able to predict the precise location of object movement in the 2-D image. The combination of these two new proposed solutions, consequently, will improve the processing time in detecting the object with precision location. 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.20aFaculty of Computer Systems and Software EngineeringxDissertations 0aUniversities and CollegesxDissertations 0aTheses40uhttp://ecollib.ump.edu.my/25914/zLibrary access only