2 Citations (Scopus)

Abstract

In recent years, technology has developed quite rapidly, especially in the field of object tracking. Moreover, if the object under study is a person and the number of people a lot. The purpose of this research is to apply Particle Filter method for tracking and counting people in certain area. Tracking people will be rather difficult if there are some obstacles, one of which is occlusion. The stages of tracking and people counting scheme in this study include pre-processing, segmentation using Gaussian Mixture Model (GMM), tracking using particle filter, and counting based on centroid. The Particle Filter method uses the estimated motion included in the model used. The test results show that the tracking and people counting can be done well with an average accuracy of 89.33% and 77.33% respectively from six videos test data. In the process of tracking people, the results are good if there is partial occlusion and no occlusion.

Original languageEnglish
Article number012059
JournalJournal of Physics: Conference Series
Volume974
Issue number1
DOIs
Publication statusPublished - 22 Mar 2018
Event3rd International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2017 - Surabaya, Indonesia
Duration: 1 Nov 20171 Nov 2017

Fingerprint

Dive into the research topics of 'Tracking and people counting using Particle Filter Method'. Together they form a unique fingerprint.

Cite this