Particle filter with Gaussian weighting for vehicle tracking

Indah Agustien Siradjuddin, Muhammad Rahmat Widyanto

Research output: Contribution to journalArticlepeer-review

Abstract

To track vehicle motion in data video, particle filter with Gaussian weighting is proposed. This method consists of four main stages. First, particles are generated to predict target's location. Second, certain particles are searched and these particles are used to build Gaussian distribution. Third, weight of all particles is calculated based on Gaussian distribution. Fourth, particles are updated based on each weight. The proposed method could reduce computational time of tracking compared to that of conventional method of particle filter, since the proposed method does not have to calculate all particles weight using likelihood function. This method has been tested on video data with car as a target object. In average, this proposed method of particle filter is 60.61% times faster than particle filter method meanwhile the accuracy of tracking with this newmethod is comparable with particle filter method, which reach up to 86.87%. Hence this method is promising for real time object tracking application.

Original languageEnglish
Pages (from-to)681-686
Number of pages6
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume15
Issue number6
DOIs
Publication statusPublished - 1 Jan 2011

Keywords

  • Bayesian
  • Filtering
  • Particle filter
  • Prediction
  • Tracking

Fingerprint

Dive into the research topics of 'Particle filter with Gaussian weighting for vehicle tracking'. Together they form a unique fingerprint.

Cite this