Dynamic Track Management in MHT for Pedestrian Tracking Using Laser Range Finder

Abdul Hadi Abd Rahman , Hairi Zamzuri, Saiful Amri Mazlan, Mohd Azizi Abdul Rahman, Yoshio Yamamoto, Saiful Bahri Samsuri

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Real time pedestrian tracking could be one of the important features for autonomous navigation. Laser Range Finder (LRF) produces accurate pedestrian data but a problem occurs when a pedestrian is represented by multiple clusters which affect the overall tracking process. Multiple Hypothesis Tracking (MHT) is a proven method to solve tracking problem but suffers a large computational cost. In this paper, a multilevel clustering of LRF data is proposed to improve the accuracy of a tracking system by adding another clustering level after the feature extraction process. A Dynamic Track Management (DTM) is introduced in MHT with multiple motion models to perform a track creation, association, and deletion. The experimental results from real time implementation prove that the proposed multiclustering is capable of producing a better performance with less computational complexity for a track management process. The proposed Dynamic Track Management is able to solve the tracking problem with lower computation time when dealing with occlusion, crossed track, and track deletion.

Original languageEnglish
Article number545204
JournalMathematical Problems in Engineering
Volume2015
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes

Fingerprint

Laser Range Finder
Range finders
Lasers
Deletion
Feature extraction
Computational complexity
Navigation
Clustering
Autonomous Navigation
Process Management
Tracking System
Occlusion
Feature Extraction
Computational Cost
Costs
Computational Complexity
Motion
Experimental Results

ASJC Scopus subject areas

  • Mathematics(all)
  • Engineering(all)

Cite this

Dynamic Track Management in MHT for Pedestrian Tracking Using Laser Range Finder. / Abd Rahman , Abdul Hadi; Zamzuri, Hairi; Mazlan, Saiful Amri; Abdul Rahman, Mohd Azizi; Yamamoto, Yoshio; Samsuri, Saiful Bahri.

In: Mathematical Problems in Engineering, Vol. 2015, 545204, 01.01.2015.

Research output: Contribution to journalArticle

Abd Rahman , Abdul Hadi ; Zamzuri, Hairi ; Mazlan, Saiful Amri ; Abdul Rahman, Mohd Azizi ; Yamamoto, Yoshio ; Samsuri, Saiful Bahri. / Dynamic Track Management in MHT for Pedestrian Tracking Using Laser Range Finder. In: Mathematical Problems in Engineering. 2015 ; Vol. 2015.
@article{6916477e97c34df8a202498afe4b6425,
title = "Dynamic Track Management in MHT for Pedestrian Tracking Using Laser Range Finder",
abstract = "Real time pedestrian tracking could be one of the important features for autonomous navigation. Laser Range Finder (LRF) produces accurate pedestrian data but a problem occurs when a pedestrian is represented by multiple clusters which affect the overall tracking process. Multiple Hypothesis Tracking (MHT) is a proven method to solve tracking problem but suffers a large computational cost. In this paper, a multilevel clustering of LRF data is proposed to improve the accuracy of a tracking system by adding another clustering level after the feature extraction process. A Dynamic Track Management (DTM) is introduced in MHT with multiple motion models to perform a track creation, association, and deletion. The experimental results from real time implementation prove that the proposed multiclustering is capable of producing a better performance with less computational complexity for a track management process. The proposed Dynamic Track Management is able to solve the tracking problem with lower computation time when dealing with occlusion, crossed track, and track deletion.",
author = "{Abd Rahman }, {Abdul Hadi} and Hairi Zamzuri and Mazlan, {Saiful Amri} and {Abdul Rahman}, {Mohd Azizi} and Yoshio Yamamoto and Samsuri, {Saiful Bahri}",
year = "2015",
month = "1",
day = "1",
doi = "10.1155/2015/545204",
language = "English",
volume = "2015",
journal = "Mathematical Problems in Engineering",
issn = "1024-123X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Dynamic Track Management in MHT for Pedestrian Tracking Using Laser Range Finder

AU - Abd Rahman , Abdul Hadi

AU - Zamzuri, Hairi

AU - Mazlan, Saiful Amri

AU - Abdul Rahman, Mohd Azizi

AU - Yamamoto, Yoshio

AU - Samsuri, Saiful Bahri

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Real time pedestrian tracking could be one of the important features for autonomous navigation. Laser Range Finder (LRF) produces accurate pedestrian data but a problem occurs when a pedestrian is represented by multiple clusters which affect the overall tracking process. Multiple Hypothesis Tracking (MHT) is a proven method to solve tracking problem but suffers a large computational cost. In this paper, a multilevel clustering of LRF data is proposed to improve the accuracy of a tracking system by adding another clustering level after the feature extraction process. A Dynamic Track Management (DTM) is introduced in MHT with multiple motion models to perform a track creation, association, and deletion. The experimental results from real time implementation prove that the proposed multiclustering is capable of producing a better performance with less computational complexity for a track management process. The proposed Dynamic Track Management is able to solve the tracking problem with lower computation time when dealing with occlusion, crossed track, and track deletion.

AB - Real time pedestrian tracking could be one of the important features for autonomous navigation. Laser Range Finder (LRF) produces accurate pedestrian data but a problem occurs when a pedestrian is represented by multiple clusters which affect the overall tracking process. Multiple Hypothesis Tracking (MHT) is a proven method to solve tracking problem but suffers a large computational cost. In this paper, a multilevel clustering of LRF data is proposed to improve the accuracy of a tracking system by adding another clustering level after the feature extraction process. A Dynamic Track Management (DTM) is introduced in MHT with multiple motion models to perform a track creation, association, and deletion. The experimental results from real time implementation prove that the proposed multiclustering is capable of producing a better performance with less computational complexity for a track management process. The proposed Dynamic Track Management is able to solve the tracking problem with lower computation time when dealing with occlusion, crossed track, and track deletion.

UR - http://www.scopus.com/inward/record.url?scp=84945311084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945311084&partnerID=8YFLogxK

U2 - 10.1155/2015/545204

DO - 10.1155/2015/545204

M3 - Article

VL - 2015

JO - Mathematical Problems in Engineering

JF - Mathematical Problems in Engineering

SN - 1024-123X

M1 - 545204

ER -