Multiple target tracking in video data using labeled random finite set

This paper demonstrates how the d-Generalized Labeled Multi-Bernoulli (d-GLMB) filter can be applied to track moving targets on videos. The tracking is performed directly on the original images which are not preprocessed into point measurements and estimates the number of targets on frame along with...

Full description

Bibliographic Details
Main Authors: Punchihewa, Y., Papi, Francesco, Hoseinnezhad, R.
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers Inc. 2015
Online Access:http://hdl.handle.net/20.500.11937/19812
_version_ 1848750136307482624
author Punchihewa, Y.
Papi, Francesco
Hoseinnezhad, R.
author_facet Punchihewa, Y.
Papi, Francesco
Hoseinnezhad, R.
author_sort Punchihewa, Y.
building Curtin Institutional Repository
collection Online Access
description This paper demonstrates how the d-Generalized Labeled Multi-Bernoulli (d-GLMB) filter can be applied to track moving targets on videos. The tracking is performed directly on the original images which are not preprocessed into point measurements and estimates the number of targets on frame along with their states. In that sense this concept bears resemblance to the track before detect (TBD) approach employed under low signal to noise ratio conditions. Image sequences from the CAVIAR1 dataset are used in simulations to prove the aptitude of this method.
first_indexed 2025-11-14T07:32:02Z
format Conference Paper
id curtin-20.500.11937-19812
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:32:02Z
publishDate 2015
publisher Institute of Electrical and Electronics Engineers Inc.
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-198122017-09-13T13:51:03Z Multiple target tracking in video data using labeled random finite set Punchihewa, Y. Papi, Francesco Hoseinnezhad, R. This paper demonstrates how the d-Generalized Labeled Multi-Bernoulli (d-GLMB) filter can be applied to track moving targets on videos. The tracking is performed directly on the original images which are not preprocessed into point measurements and estimates the number of targets on frame along with their states. In that sense this concept bears resemblance to the track before detect (TBD) approach employed under low signal to noise ratio conditions. Image sequences from the CAVIAR1 dataset are used in simulations to prove the aptitude of this method. 2015 Conference Paper http://hdl.handle.net/20.500.11937/19812 10.1109/ICCAIS.2014.7020543 Institute of Electrical and Electronics Engineers Inc. restricted
spellingShingle Punchihewa, Y.
Papi, Francesco
Hoseinnezhad, R.
Multiple target tracking in video data using labeled random finite set
title Multiple target tracking in video data using labeled random finite set
title_full Multiple target tracking in video data using labeled random finite set
title_fullStr Multiple target tracking in video data using labeled random finite set
title_full_unstemmed Multiple target tracking in video data using labeled random finite set
title_short Multiple target tracking in video data using labeled random finite set
title_sort multiple target tracking in video data using labeled random finite set
url http://hdl.handle.net/20.500.11937/19812